Podcasts about SEM

In this Marketing Over Coffee: Learn about what’s going on at OpenAI, How Trust Insights can teach you to use Generative AI, What Gear to Buy, and more! Direct Link to File Brought to you by our sponsor: The New Generative AI for Marketing Course from Trust Insights What’s going on at OpenAI? What should […] The post Use Generative AI for Marketing! appeared first on Marketing Over Coffee Marketing Podcast.

El espectáculo que Chico Buarque lleva presentando en concierto desde septiembre de 2022, 'Qué tal um samba?', llega ahora en forma de disco doble. Con la cantante Mônica Salmaso como invitada muy especial ('Mar e lua', 'Passaredo', 'Beatriz'), con Mônica y Chico cantando juntos ('Paratodos', 'O velho Francisco', 'Sinhã', 'Sem fantasia', 'Biscate', 'Imagina') y con Chico Buarque ('Morro dois irmãos', 'Futuros amantes', 'Assentamento', 'Bancarrota blues', 'Tua cantiga', 'Meu guri'). Escuchar audio

Get ready to take your Walmart selling game to the next level! Our brilliant guest, Michal Chapnick, a Walmart expert, talks about Walmart's ad certification, the unveiling of innovative beta programs, and the integration of Google ads into promoting your Walmart products. She'll also shed light on Walmart's commitment to third-party sellers through initiatives like fee discounts and personalized product suggestions. This is the inside scoop you need to unlock the potential of Walmart's marketplace and see your sales soar. Discover the power of Google ads in driving traffic to Walmart and how it can work wonders for your brand exposure. Dive into the advantages of Walmart's SEM program and learn why it may be more beneficial than directly sending Google ads to Walmart. Michal reveals the abundant opportunities awaiting sellers at Walmart Canada and uncovers the potential impact of beta programs, such as brand stores, on your sales figures. This Walmart Wednesday episode is packed with insights and advice for those seeking to extend their business reach on Walmart. As we approach Q4, the busiest time for e-commerce, Michal shares her expertise on maximizing your sales during this hectic period. From planning and implementing promotions to optimizing your listings and enhancing customer service, we've got you covered. Uncover the impact of the beta version of coupon codes and the power of video ads in holding customer attention. We wrap up our episode by acknowledging all the diligent sellers out there and remind you to make the most of the opportunities available on Walmart's platform, particularly during the holiday season. Buckle up for a wealth of knowledge, and best wishes for a profitable Q4!   In episode 513 of the Serious Sellers Podcast, Carrie and Michal discuss: 00:00 - Selling on Walmart Updates and Opportunities 03:13 - BIS Mentor and Customized Suggestions 06:07 - The Growth and Opportunities With Walmart 12:35 - Walmart's Influence on Black Friday Sales 15:23 - Running Ads for Walmart Benefits 19:17 - Opportunities for Selling in Walmart Canada  23:53 - Promoting Walmart Sales With Coupons and Videos 31:56 - Optimizing Keywords With Helium 10 33:24 - Q4 Selling Tactics and Appreciation ► Instagram: instagram.com/serioussellerspodcast ► Free Amazon Seller Chrome Extension: https://h10.me/extension ► Sign Up For Helium 10: https://h10.me/signup  (Use SSP10 To Save 10% For Life) ► Learn How To Sell on Amazon: https://h10.me/ft ► Watch The Podcasts On YouTube: youtube.com/@Helium10/videos Transcript Carrie Miller: On today's episode we have Walmart expert Michal Chapnick. She's going to be talking about Walmart ad certification, new beta programs for Walmart, as well as Google ads for Walmart. So this and so much more on today's episode of the Serious Sellers Podcast.   Bradley Sutton: How cool is that? Pretty cool, I think.   Carrie Miller: Hello everyone and welcome to another episode of the Serious Sellers Podcast by Helium 10. My name is Carrie and I'm your host today, and this is our winning with Walmart Wednesday, where we talk about all things Walmart. We answer all of your questions and I'm very, very excited today because I have an amazing guest. We have Michal Chapnick, who is going to be joining me. I'm going to be asking her lots of questions because she's a Walmart expert. She has a Walmart agency and she's had a lot of success on Walmart. I know a lot of you are familiar with her. Hey, Michal, how's it going?   Michal: Hello, I'm good and good. How are you doing?   Carrie Miller: Very good. Thank you, nice to see you, and thanks so much for coming on. I'm really excited to have you because you're one of the you know Walmart gurus one of the few Walmart gurus. I would say, probably one of the top in the industry here for Walmart. So thank you. Yeah, so I'm really excited because I know that you have a lot of kind of cool updates to share with us. Okay, so I'm going to get into it. I'm going to get into some of the first things. I'm going to ask you just what kind of updates are there that you would like to share with us about Walmart? Do you want to share any updates of anything new for Walmart or what's new?   Michal: basically, I think there are so many Recently. You know, every week we do Walmart updates and we have, like you know, 10, 15 slides every week because they're really on top of it, they're working really hard and a lot of them are really exciting because and I'm telling that all the time Walmart really wants you. They want you on Walmart, they want the brand, they want you to sell and a lot of people you know sometimes having a hard time to enter Walmart or when they're on Walmart they're having a hard time to sell. But Walmart really wants you there and they're doing everything they can from their side to help you and, you know, give you help to set up, give you help with fees. There's always some kind of promotion there is doing for sellers that are already on Walmart or new sellers. So right now they're doing a lot of like. They're cutting off fees in different ways.   Michal: So either if you have the Pro Seller badge and you can get deep discounts on fees and you can get credit that you can use it for run ads or to use it for the review accelerator program, so you get this credit back. The only thing you need to do is go to your BIS mentor. It's in every account. It's on the, I think, top left and Walmart is giving you customized suggestions so it just specifically for you.   Michal: So from things like items that they think you have an opportunity to get more sales if you lower your price and they're willing to cut your sell off fees, so they will cut your sell off fees so you'll be able to take your price lower to sell more. So this is just one example of the second thing they will give you like a customized list of products that they think you should add to your account. So they're basing that, based on the category you're selling or the brand you're selling. So if you're a resale, of wholesale, you will see a lot of opportunities and I know that some of my sellers that I'm working with they're taking really good advantage of those and they're they managed to get a lot of sales because usually Walmart will tell you something that is out of stock or something that the other sellers are not using WFS.   Carrie Miller: So once you got this inventory and it's already selling very well and you're the only one selling it or the only one WFS, imagine that is like so much self I actually talked to them about this and they said that they anything in the assortment growth tab, that those are really the best opportunities because they kind of compliment what they already have on Walmart. So they're looking for complimentary products. So I think that's why is they're really going to. If you take those suggestions, they're going to boost you and then you're going to get a lot of exposure and sales. Like I know, I was talking to an account manager and she said that somebody in the toys category had a bunch of assortment growth suggestions for toys and they started manufacturing them and basically have been killing it on Walmart, just making tons and tons of sales. So that's a that's something that is really interesting right now for opportunity for selling products.   Michal: It is working. I know that one of our clients that he have an account manager. You know in the past you know they were doing it personally, they know exactly the opportunity so they can do it all and you know he's selling in the category of backpacks. They told him you know what styles right now there is like a lot of demand, for example, clear backpacks and things like that, and the same thing is killing they're. They're making six figures a month.   Michal: They're just amazing. So Walmart is there to help you. I think, if you, I don't know I was selling on Amazon for 12 years, but I remember the 10 years ago. I used to get emails from Amazon every day with items to sell. They were like telling me hey, you know these these, you know those items right, and I don't know if they still do that. I have no idea, but I haven't gotten any recently. And but with Walmart is the same thing. They want to know.   Michal: For them to get to the same or as close as Amazon sells, their catalog have to grow and that's their focus. They're focused in growing their catalog and they're using the sellers, the third-party sellers, to leverage the catalog. There's still far away in a couple of hundreds of millions of products from Amazon. There is so much place for new sellers and even people that come into Walmart and they're new and they don't know what to sell. I can show them so quickly. So much opportunities. There's endless opportunities. One of the coolest things with the mentor base even if you're a private label, walmart know you're selling, for example, in the toy category or kitchen, and they know exactly what product, have a lot of demand and they will tell you. And then you need to go and manufacture that or source that or there's so many ways you can get your hands on these items. This is one of the things that I really like, that they're really encouraging you and we just talked about it.   Michal: Right now they have an update for the category of automotive. They will tell you all the products they're looking for in automotive and they tell you please bring those products, list them. We want you to create the listing. They do not want you to sell something. Yeah, of course you can sell. Something is already on Walmart but what they're trying to do is to get you to create new listings. They want you to not just to create new listing. They also expect to need to create good listings, because when they're good listing, they can be in front of customers. Customer can find them. When customer find it, the content is good, so he will buy it.   Michal: Right now they give you the option to upload videos to your listing. Everybody can do that right now. It doesn't cost you anything. You can just go ahead and there's a when you go and open the case. There is one of the section it says upload rich media, upload video, and they will give you an instructions and a file to upload your video. So they're really doing a lot for the sellers and going a little bit back. The most important things that you need to remember is that you have to follow the guidelines, because you're going to have so much benefits coming after that, Getting the processor batch, for example. Now they're offering the SEM, that's the searching agent marketing, and what is that? So let's talk about that for a second, because that's I think this is one of the most exciting updates the last couple of months.   Carrie Miller: Yeah, I saw it pop in my account and I took a look at it. I think my biggest question is because this is basically advertising through Google Shopping, through the portal, and they basically do it for you. As long as you're really well optimized, you'll show for the best keywords. But is this now the paid version of what was free? Because I remember my product used to show up a ton on Google Shopping just for free and I hadn't been advertising on Google for Walmart but it would say available on Walmart.com. Is it now kind of paid and not free, or do you see both?   Michal: No, it's definitely both. So here's the secret. Walmart is spending millions Even I wish I could see their budget for Google Ads. It's insane, it's really crazy. They know the power of Google Ads. We saw in many, many clients a lot of time when we went deep into the sales and trying to understand where those sales are coming from. Between 30% to 40% of a lot of item sales coming from Google Ads. So Walmart is pushing all the listing to Google Ads.   Michal: But there's a couple of criterias, like your listing have to be following the guidelines, you have to have good images, so you have to have not too long title and all the things that are very important, and you can see it in your listing score. There is a tool that show you exactly the score for every little part of your listing and if your score is high, there is no reason why you shouldn't be eligible to show up on Google Ads. So Walmart is not going to put you on Google Ads if you don't have enough images, because then the pain for your item to show up on Google a customer is going to click on that is going to come to Walmart and he's not going to end up buying because there's no information or there's no images. So again, they have to make sure your listing is going to have the chance to convert before they will do that. So the only thing you need to do is make sure your listing is following the guidelines. And so now Walmart is telling you we're giving you the option. We know how powerful is Google, we know how powerful the ads are coming. We are spending a lot of money, but if you want to do some extra, you want to spend more money, you want to put more product. We're giving you the option to start doing campaigns on Google, and I think that's huge and I think whoever is going to take advantage of that is going to see amazing results in their conversion rates.   Michal: Because Still, 40 percent of people will start their search on Google. I think 35 percent going to go directly to Amazon, 40 percent on Search and Agent, and then the rest is spread on different things. Some people will go through Pinterest or even social media. They're going to look and stuff in there. Another thing that why you want to be optimized is the same thing as more you optimize and you listen to high quality. Walmart is not just advertising on Google or Bing or Ad. They're advertising with a lot of social media advertising, with a lot of bills website. They're advertising with a lot of really big influencers that they're paying them a lot of money. As more as you're listening is good. They will expose your items to all those channels they're advertising at.   Carrie Miller: That's possible. Yeah, I know that.   Michal: Yeah, I was talking with one of the account manager and they have the option to pick items and put them on this bucket, this list, and then website deals website like a silk deals, and there's all websites like that or influencers have the option to look at that list and pick the items they want to promote this week because they're getting paid and they get also getting paid affiliates. Yeah, there's things like that. Sometimes, if you follow influencers on Walmart on Instagram, they're doing a lot of Walmart. You can see they're pushing a lot of passion. Yeah, kitchen items. And right now it's crazy because people are waiting for influencers to show them what's the deals on Walmart, because everybody know that Walmart have the best Black Friday deals.   Michal: Yeah, we always have the biggest selection, the biggest selection of deals in each category. Because other stores can be just electronics, best buy with Walmart. The Black Friday deals are on home, on outdoor, on Christmas decoration, toys, clothing, jewelry, everything. Walmart is very known in Black Friday.   Carrie Miller: We did have a question about SEM. It says do you do Walmart SEM and your own Google ads at the same time? That's a really good question Because if you don't want to cannibalize your own Google ads while doing the SEM Google ads, that is a really good question.   Michal: Usually, when you do your own Google ads, you choose where the traffic is going to go. You can run Google ads for your website. It's good because many times I remember I had items that I used to sell in the past. There were not all of people were selling them In the category. I would say it was a kind of a shoes, a specific shoes for kids. When I used to go to Google and I used to write that specific keyword. I get Google ads and I sell my shoes on Walmart. Next to it I saw my shoes on my website and next to it on Amazon. I used to get all the Google ads I could. Now, most likely, the customer will buy my shoes. It doesn't matter where, but he will buy them. Again, you're creating brand awareness. It's more ads you can create. It's more exposure. You can put your brand in a product. It's better for you because the customer remembered that.   Carrie Miller: I think that they clarified it. I mean sending Google traffic to Walmart. Maybe not do your own Google ads to Walmart if you're doing SEM, potentially.   Michal: Yeah, that's what it's going to do. That's exactly what it's going to drive traffic from Google to your Walmart. So I say you know, try, try, you can put a budget. It's not too complicated to run those campaigns. So I would say, give it a try. And before you do that, also go and search for your item on Google and see if it's really coming up, if Walmart is already promoting your items. And again, the most important thing, make sure your listing is following the guideline.   Carrie Miller: Yeah, for my own Google ads. I did do an experiment where I was trying to see if it would help with ranking if I sent outside ads, like from Google, like at U-Kan on Amazon, and I noticed that it did not make a difference when I sent my own Google ads to Walmart. And so I think that probably, if there is going to be a benefit, it's probably going to be through the SEM program doing ads to Walmart. So if if I were to choose between the two, I would probably do the Walmart SEM over Google to my own Google ads to Walmart, whereas I would still obviously do Google ads because I have Google ads to my own sites as well. But that's what I would think because I know that they are kind of looking at their own metrics and the more you convert on their side, I think that the better it is. But that could be just a guess, but I do know for a test that it did not help my rank. So there is that, because I know a lot of us do that for Amazon. We send Google traffic and it does help with rank, but it didn't on Walmart.   Michal: Yeah, one more thing I'm thinking of is that it's probably going to be much better because they have better pricing, so it might be going to end up being much cheaper than you spend it yourself.   Carrie Miller: Yes, it's Walmart.   Michal: It's going for Walmart account. It's not your Google account, it's Walmart account having their own pricing. So you will get that. And the second thing it's known because I can see it. Every time I go to Google I can see Google love Walmart. Google will always place Walmart ads in first five. So this is another thing you will get better exposure and you have better chance to shop in a better ad in a better location Because, again, it's through Walmart. So just that it's worth it.   Carrie Miller: We have another question. Actually Bradley asked this one and it says is Walmart Canada worth it yet?   Michal: I absolutely think so, absolutely. It is very like with Walmart.com, the same thing with Walmart Canada. Not every product will be a huge success because those marketplaces are still building their customer base, but I think Walmart.com is doing very good. Now for Canada, from a lot of people that I have a lot of friends that live in Canada people online. When they go online they usually will go either to Amazon Canada or Walmart Canada. There is not too many options. Some items people can go to the store and have some problems to find Like there is not always big selection of things. So if you know to find those items that people having a hard time to find in the store or next to their house, you will know that Canada will be very, very good.   Michal: So actually, going back to the time when I used to sell kitchens, we had exact same styles on that farm in Canada and actually it was a period of time that we met sales on Canada. Because I guess you know people need, you know everybody needs shoes for their. Yeah, you don't need to do much, it's going to sell. If you have nice shoes with quality, it will sell. And I think the thing is that, again, people when they go online, they don't. There's not too many brands that are selling on Walmart.com or Canada. So again, if you find those opportunities and there is tons of opportunities on Walmart Canada and also in Canada people, the Canadian, are paying high prices on stuff, so you don't have to sell nothing to cheap, you can sell it in your price or even higher and customers are paying and they're also paying shipping as well, so I think the profit is also very nice on Canada.   Carrie Miller: All right, let's go into some other things I know. Can you give us some insights to you know, like I think, some beta programs I think coupons, brand stores, any other kind of beta programs that you've seen, and have you been able to use them and what's your experience been with those?   Michal: Yeah, so brand stores are available for very selected amount of sellers. Right now it's mostly they started with a lot of sellers that do it fashion, so we do have a couple of our clients that they have the option to do brand stores and right now it looks great. I cannot wait for it to be available to everyone because we need that. You know you want to click on the brand and go to a nice storefront that you can display your. You know what are you selling. I think it's going to help a brand grow really nicely on Walmart and I think the best part is, again we see the people that selling on Walmart. There's not a lot of brands that take Walmart really seriously and doing those extra steps, but the one they do, those that want to see really success on Walmart. So I'm excited to you know, to see some of the brands we're working with, you know, using that feature and growing. The second thing is coupon codes. So coupon codes again are in beta right now. Yes, and it's available from whatever.   Michal: Only like 50 sellers got that, yeah, maybe now a little bit more, but I cannot wait for that because, again, this is huge for doing social media marketing, because people love those videos and those ads and everything that you give them. Coupon code is, like, so popular right now with Amazon, and I think it's going to help get so much more traffic and sales to Walmart when you can, you know, and display your items with the coupon code. I think so.   Carrie Miller: I think that it's a bummer we don't have it right now because my sales when we started doing a coupon on Amazon have done really, really well, because I just think people are always looking for a deal. So, seeing that coupon, they're like, oh, I might as well just get this item too in here because it's on sale or there's a coupon, whereas you know we don't have it on Walmart yet. I'm kind of antsy to get coupons on Walmart. It would be really cool if they just decided next week to release those, because I'm desperately waiting for those because they work really well on Amazon. We see that they work because people are already shopping on there and they're like, oh, I'm looking, they're looking for deals, right? So the more access we have to give deals, I think, the more sales we're going to make on Walmart.   Michal: So, yeah, in beta anymore. It's available to everyone. If you're a brand, you have to be brand and register, but is the video ads. Yes is the most exciting thing I think happened recently for brands is that you can create a video ad and you get your customer attention so fast because you know the minute they search for something, your video is and it's big, it's really big. You saw on Walmart, it's not like tiny. It's like yes, really like the page. It's really nice big deal, and I'm still amazed that so many brands are not using that. There are so many people and sellers that are not using the video ads or even just to upload the video to the listing. So many people are not doing that. So and so, yeah, this is I think the key to this with Walmart is paying attention and doing all this stuff. I agree.   Carrie Miller: I think I've talked to some people and because the minimum is a dollar for the video ads, they haven't been utilizing them. Have you started doing video ads and have you seen some good conversion on those, like just better conversion overall? Or what do you see with the video ads Currently?   Michal: yeah, we do have one of our clients that is running video ads and their sales are are really going high, Like we're talking about 30% more than before, so that's really nice. They're very happy with that, and so this is one of the things that you know with advertisement usually you should see growth and you know with sales.   Carrie Miller: Mm, hmm, that would be. Yeah, that's amazing. Okay, so let's see, there was something else that you mentioned, and it was ad certification. Do you want to talk a little bit about Walmart ad certification? I think this is a completely new program, so yeah, that's a new program that Walmart is.   Michal: see that people struggling with ads Like they're trying to run ads and they don't know, they have no clue what they're doing. So they're saying, hey, let's give you a certificate. So I think it's just to make people feel like, oh, if they're going to go through a course, they're going to be certified and they know what they're doing. So this is what they're trying to do. Or they're even offering that to your team. It doesn't have to be you, it's going to be somebody from your team. So if you have a VA, or because Walmart advertisement is not difficult, but you have to take the time and and learn how to create your campaigns correctly, how to optimize them, how to find the right keywords, a check your competition.   Michal: If you're running ads and you don't spy on your only competitors to see what they're doing, you're missing out. Because this can be. I always find. When I do, you know, when I look at competitors, when we run ads for customers, we can always see that there is, we have a list of all the relevant keywords and then we look at the competitors and sometimes they're missing one or two, or sometimes even more. And that's your opportunity. So I think it's just to make sure that you're not missing out, and so we can always see that there is.   Michal: We have a list of all the relevant keywords and then we look at the competitors and sometimes they're missing one or two or sometimes even more. And that's your opportunity, because nobody's paying for that keywords and you can pay for it and get all the traffic. Or Another thing that I see all the time with the competitors is that they're paying for a lot of phrases but they're not coming out as relevant because they don't have that phrase in the listing. So the ad algorithm is very smart, so he will sometimes place them for these keywords, but only because they don't have somebody that looks more relevant. Once you come and you're more relevant, you're not really competing with him because you will always get the first spot in the first page because the algorithm know you're relevant. So it's easy. Even if somebody in your confederate is advertising sometimes they're not doing such a good job you can always come and find those little holes where you can take advantage of something that your competitor is not doing.   Carrie Miller: Very good, very interesting. Well, I think we're pretty much at our time limit, but I was wondering if there's anything else that we didn't talk about that you might want to give advice on or share with the audience. Any final thoughts?   Michal: Yes, I think through the end of the year. Right now it's a really good timing for a lot, especially of the new seller, to see the potential of Walmart because a lot of them will be surprised right now with the sales. So I really want a lot of you to catch the momentum of the end of the year. Right now it's the best timing to add new product because there's a lot of traffic. So take the time and add new product. If you have a product they're doing very well, sometimes you can even just create another offer. It can be two-pack, three-pack, it can be a bundle. Again, it's more items you add, more customer can find you, you create more brand awareness. So add as many skills, as I always think is a good strategy to build your brand and stay in stock, even though pay attention, because a lot of people what happened right now? They're getting out of stock because they didn't thought they're going to sell so many, so much on Walmart and they're getting out of stock quickly. So try to stay in stock so you keep your momentum and your ranking. So add, advertise. Now is the best time.   Michal: Advertise, pay attention to your budget. Make sure you're running ads during those peak days and peak hours. You don't run out of your budget too early of the day, so take advantage of the Google advertisement promo code. One thing that I wanted to say it's going to be super cool when you run ads. So your item is showing up like write the first thing the customer seat and then you use a promo. Like promo it's mean you're doing something like reduce price. So your item right now instead of $29.99 is $24.99. So you already catching the customer eye because you can see this item is on sale and then they click on your product and then they see there is coupon code. Right, it's going to be like. I think it's going to create a lot of conversion.   Carrie Miller: I think so too.   Michal: Together, and so I cannot wait for the coupon code to come. But right now you can run ads, you can do promo and that's going to catch some eyes. You will get a lot of sales just by doing that, as well as running ads going to help you get ranked. So this is a really good timing to not just sit back and say, oh, it's too late. No, it's not too late, you have enough time. Continue optimizing. Even right now. I'm telling all our customers please run a new keyword report.   Michal: One of the things that people don't do is everybody that listen right now. When the last time you optimize your listening maybe you upload a year ago did you optimize it since then? Keywords is something that change all the time, especially in Q4. Because in Q4 there's a lot of new phrases. So if you sell toy for girls and right now you can add something to one of your key features, it says that toy make a great Christmas gift for girls. Christmas gift for girls is a very high search term at this time of the year and if you don't use it, you're missing out thousands of thousands of customers that potentially can come to your listening because that phrase is in your listening. So it's the perfect time right now, today, or even if you're on vacation or something next week, whenever you listen to that at any time.   Michal: Go to Helium 10, run keyword refresh, keyword report to your product and do a couple of adjustments. Go and add those keywords to your description, to your title, even to your key features. Even your attributes can use some refreshment. Go to your listing tool score and see your score and see what you can improve in there. So just by doing that and you know what I love about it, that if you do that, you will see that in the next week or two you will get more traffic. It's working, guys. I think this tip is always working.   Carrie Miller: One more question on that Do you use Helium 10, Cerebro and Magnet to find those keywords, or where are you finding those keywords? Is that kind of the best option?   Michal: I'm using both. So Magnet, we're always doing searches just to see what's coming up, and I always like to use Cerebro because I will go to my competing items. At least two or three of them will take their item number, go to Cerebro to see what they're ranking for, which keywords, and almost always I will find the phrase that I never got in the other search. So always do both.   Carrie Miller: Yeah, we're updating those keywords every week, so you should be able to find new keywords on Helium 10, Cerebro and Magnet. So thank you everyone for listening. Thank you so much, Michal, for coming on. I always love having you on because you are definitely one of the top in the industry, so I appreciate you taking the time and answering questions and giving advice. So good luck to everyone who's selling this Q4. I think we've gotten a lot of really great tactics here from Michal on what to do, from you know, for Q4. So we will see you all next time on Walmart Wednesday. So thank you.   Michal: Bye Carrie. Thank you so much.   Carrie Miller: Bye.  

Vamos ver agora 5 efeitos colaterais negativos do corte severo de carboidratos que a maioria das pessoas ainda desconhece e que nem mesmo muitos daqueles que ainda promove low carb sabem que acontece, alias, eu senti na pele todos eles e talvez você também...  Você vai entender como low carb pode em tempo desacelerar seu metabolismo, sua tireoide, atrapalhar seu bem-estar e sono e levar você até a ganhar peso com mais facilidade!  Veja o vídeo e passe a frente!  Forte abraço,  Rodrigo * Você já tentou um método METABÓLICO de emagrecimento? 

Adquira meu livro Lugar de Potência: Lições de carreira e liderança de mais de 10 mil entrevistas, cafés e reuniões

Trouxemos o Rodrigo Vignoli do Diário Mágicko para falar sobre Limpezas energéticas! Já pensou em limpar aí o que você sujou? ORÁCULO DAS 7 LINHAS DE UMBANDA E QUIMBANDA O método oracular desenvolvido por Douglas Rainho em parceria com Tata Kamuxinzela para aprimorar a comunicação com os espíritos tutelares de Umbanda. Com este oráculo você será capaz de responder as inquietações espirituais, materiais e práticas dos seus consulentes, além de ter direcionamento para o uso das medicinas espirituais adequada. Este oráculo está em conformidade com o COSMOS da Umbanda e é uma ferramenta útil para todo dirigente espiritual, médium, feiticeiro e oraculista. Tenha suas perguntas respondidas, descubra os caboclos, pretos-velhos, exu e pombagiras tutelares dos seus consulentes. Acesse agora mesmo www.oraculodeumbanda.com.br e faça parte dessa jornada. Este episódio foi transmitido no dia 25 de Novembro de 2023, às 21 horas. Apoie o Papo na Encruza: Sendo um apoiador você nos ajuda a manter a estrutura do blog e do podcast em alto nível. Também irá concorrer a diversos prêmios conforme a sua categoria de apoio. Quer ganhar descontos em nossos cursos, concorrer a sorteios de livros e de outros itens? Fazer parte do Umbral, nosso grupo no Telegram? Clica abaixo e nos apoie! =) Seja um apoiador do Papo na Encruza no Catarse e concorra a diversos prêmios Livros Recomendados: Conhecendo a Umbanda: Dentro do Terreiro, o livro de Umbanda escrito pelo Douglas Rainho e lançado pela Editora Nova Senda. E-Book: O Espiritismo, a Magia e as Sete Linhas de Umbanda - Leal de Souza E-Book: Guia do Praticante da Umbanda - Douglas Rainho  Confira TODA nossa Bibliografia Recomendada. Citado no Episódio: Cursos no PerdidoEAD: Um local para conhecer e praticar. Oráculo de Exu com Douglas Rainho. Aprenda a Ler o Oráculo das 7 Linhas de Umbanda e Quimbanda. Redes Sociais: Grupo do Facebook: Papo na Encruza - PODCAST Facebook do Papo na Encruza Instagram Papo na Encruza (@paponaencruza) Instagram Douglas Rainho (@douglasrainho7) Instagram Luiz Guenca (@guenca) Instagram Cova de Tiriri (@covadetiriri) Fale com a gente Caso queira entrar em contato conosco, para enviar dúvidas, comentários e sugestões, nosso e-mail é contato@perdido.co. Muito obrigado todos os nossos apoiadores! Sem vocês esse programa não poderia acontecer!

Foi aprovado nessa semana um projeto de lei com relatoria do partido NOVO, que reduz os custos de INSS e FGTS na contratação de jovens no Brasil, e isso atinge diretamente as periferias. Jovens negros, pardos e periféricos são prejudicados no mercado de trabalho por incompetência do estado. Sem educação, saneamento e segurança, não competem de igual pra igual com quem vem de bairros centrais. É importante reconhecer que existe essa divisão social e que combater isso é papo de libertário, porque apenas a liberdade pode dar melhores condições de vida para essas pessoas. Como disse Milton Friedman, salário mínimo é racista! Quer fugir do Brasil? Nos contate: https://www.settee.io/ https://youtube.com/c/Setteeio Nos acompanhe no Telegram: https://t.me/ideiasradicais Quer comprar Bitcoin no melhor preço do mercado? Bity! https://bit.ly/BityIdeiasRadicais

In this enlightening episode of the Marketing Guides for Small Business Podcast, we demystify the ever-important world of SEO - Search Engine Optimization. Designed for both newcomers and seasoned marketers, this episode breaks down the fundamental concepts of SEO, its significance in the digital age, and advanced strategies to enhance your online presence. Whether you're just starting out or looking to refine your existing knowledge, this episode is your guide to understanding and leveraging SEO effectively. Episode Highlights: SEO Defined: A clear and concise explanation of what SEO is and why it's essential for online visibility and success.Key Components of SEO: Understanding the pillars of SEO, including keywords, content, on-page optimization, backlinks, and user experience.Why is SEO important?How does SEO differ from SEM and PPC?What are the 3 types of SEO?How do search engines and SEO work?How does website hosting fit into the SEO conversation and what is it's impact?Does cheap website hosting cut it for SEO?What is the impact of a website refresh or redesign on your Google rankings and SEO? By the end of this episode, you'll have a solid grasp of SEO fundamentals, an understanding of advanced tactics, and the knowledge to implement effective SEO strategies for your business. Tune in to elevate your SEO game!

Scopri la Bibbia un versetto per volta con semplici commenti dell'insegnante Egidio Annunziata.LETTURA DELLA SACRA BIBBIAGenesi 10 - https://www.bible.com/it/bible...1 Questa è la discendenza dei figli di Noè: Sem, Cam e Iafet; a loro nacquero dei figli dopo il diluvio.2 I figli di Iafet furono: Gomer, Magog, Madai, Iavan, Tubal, Mesec e Tiras.3 I figli di Gomer furono: Aschenaz, Rifat e Togarma.4 I figli di Iavan furono: Elisa, Tarsis, Chittim e Dodanim.5 Da costoro derivarono i popoli sparsi nelle isole delle nazioni, nei loro diversi paesi, ciascuno secondo la propria lingua, secondo le loro famiglie, nelle loro nazioni.6 I figli di Cam furono: Cus, Misraim, Put e Canaan.7 I figli di Cus furono: Seba, Avila, Sabta, Raama e Sabteca; i figli di Raama: Seba e Dedan.8 Cus generò Nimrod, che cominciò a essere potente sulla terra.9 Egli fu un potente cacciatore davanti al Signore; perciò si dice: «Come Nimrod, potente cacciatore davanti al Signore».10 Il principio del suo regno fu Babel, Erec, Accad e Calne nel paese di Scinear.11 Da quel paese andò in Assiria e costruì Ninive, Recobot-Ir e Cala;12 e tra Ninive e Cala, Resen, la grande città.13 Misraim generò i Ludim, gli Anamim, i Leabim, i Naftuim,14 i Patrusim, i Casluim (da dove uscirono i Filistei) e i Caftorim.15 Canaan generò Sidon, suo primogenito, e Chet,16 e i Gebusei, gli Amorei, i Ghirgasei,17 gli Ivvei, gli Archei, i Sinei,18 gli Arvadei, i Semarei e i Camatei. Poi le famiglie dei Cananei si sparsero.19 I confini dei Cananei andarono da Sidon, in direzione di Gherar, fino a Gaza e in direzione di Sodoma, Gomorra, Adma e Seboim fino a Lesa.20 Questi sono i figli di Cam, secondo le loro famiglie, secondo le loro lingue, nei loro paesi, nelle loro nazioni.21 Anche a Sem, padre di tutti i figli di Eber e fratello maggiore di Iafet, nacquero dei figli.22 I figli di Sem furono: Elam, Assur, Arpacsad, Lud e Aram.23 I figli di Aram furono: Uz, Ul, Gheter e Mas.24 Arpacsad generò Sela, e Sela generò Eber.25 A Eber nacquero due figli; il nome dell'uno fu Peleg, perché ai suoi giorni la terra fu spartita; e il nome di suo fratello fu Ioctan.26 Ioctan generò Almodad, Selef, Asarmavet, Iera,27 Adoram, Uzal, Dicla,28 Obal, Abimael, Seba,29 Ofir, Avila e Iobab. Tutti questi furono figli di Ioctan.30 La loro dimora era sulla montagna orientale, da Mesa in direzione di Sefar.31 Questi sono i figli di Sem, secondo le loro famiglie, secondo le loro lingue, nei loro paesi, secondo le loro nazioni.32 Queste sono le famiglie dei figli di Noè, secondo le loro generazioni, nelle loro nazioni; da essi uscirono le nazioni che si sparsero sulla terra dopo il diluvio.Isaia 1 - https://www.bible.com/it/bible...Galati 5 - https://www.bible.com/it/bible...Matteo 5 - https://www.bible.com/it/bible...Genesi 6 - https://www.bible.com/it/bible...2 Pietro 2 - https://www.bible.com/it/bible...Episodio: Genesi 10Conduttore: Egidio AnnunziataLuogo: Nocera Inferiore, Salerno - ItalyEvento: Incontro domenicale della comunità Essere Un CristianoData: 26/02/2023Lingua: ItalianaProduzione: © Essere Un Cristiano 2023

Sermão pregado pelo Sem. Leonardo Barros na Igreja Presbiteriana de Cascadura. Acesse o nosso site: https://cascadura.ipb.org.br/ https://www.instagram.com/ipcascadura/

No podcast ‘Notícia No Seu Tempo', confira em áudio as principais notícias da edição impressa do jornal ‘O Estado de S.Paulo' desta segunda-feira (20/11/2023): Com discurso polêmico e a promessa de fazer cortes radicais no Estado argentino, incluindo a “implosão” do Banco Central, o libertário Javier Milei derrotou o peronista Sergio Massa e assumirá o governo da Argentina a partir de 10 de dezembro. O comparecimento às urnas chegou a 76%, e Milei obteve 55,8% dos votos, a maior vantagem de um candidato a presidente em eleições recentes naquele país – as pesquisas apontavam para uma disputa mais acirrada. A vitória expressiva do candidato ultraliberal também surpreendeu o Planalto, que não esperava diferença de votos tão grande. Sem citar o vencedor, Lula desejou “sorte e êxito” ao novo governo. Milei na Casa Rosada levanta uma série de dúvidas, incluindo o futuro da relação com o Brasil e o Mercosul. E mais: Internacional: Israel e Catar afirmam que acordo com Hamas sobre reféns está perto Metrópole: Guarujá quer controlar acesso a uma das suas praias mais bonitas Economia: Varejo teme mudança de regra para trabalho aos domingos e feriados Política: STF tem 40 ações contra políticos que se arrastam há mais de 3 anos Esportes: Verstappen vence pela 18ª vez no ano e Pérez garante o viceSee omnystudio.com/listener for privacy information.

Fala, Fala minha Amiga, meu Amigo BIOENERGÉTICO!  A tecnologia está DESTRUINDO a sua SAÚDE e você nem sabe disso.  Ou se sabe… …Não faz a MÍNIMA IDEIA sobre como se proteger.  Foi pensando nisso que gravamos esse episódio  Se você não aprender o que compartilhamos aqui ousamos te dizer que você JAMAIS irá viver o potencial máximo da sua saúde… …Nem reverter problemas CRÔNICOS! Por isso, confira o episódio agora mesmo escolhendo sua mídia favorita logo abaixo: LINKS Depois de escutar este episódio do Projeto Energia Crônica, visite nosso site http://www.projetoenergiacronica.com para saber mais sobre a Revolucionária Biomodulação Energética Integrada que é capaz de te energizar e transformar sua saúde de uma vez por todas! ❌SEM tomar medicamentos perigosos e contínuos. ❌SEM dietas milagrosas. ❌SEM privar-se das coisas boas da vida. (mesmo que você tenha apenas 15 minutos durante seu dia) Tenha um ótimo dia e até a próxima!! Vanessa e Bruno  Fundadores do Projeto Energia Crônica

Hoje vamos dar uma volta ao mundo pelos paises mais magros e vermos o que eles tem em comum em questão da dieta. Vamos ver quais são os “segredos” destas populações que ainda mantem a forma em um mundo que fica cada vez mais obeso. Aproveite :)   ▶️ Vídeos recomendados:  - 9 Gorduras ÓTIMAS e 4 PÉSSIMAS Para Fritar e Cozinhar | Óleos, Ponto de Fumaça, Oxidação, Sabor  https://www.youtube.com/watch?v=BNm8K4idgAE&t=180s  - Este Óleo Comum Faz Você Engordar e Dá Fome!  https://www.youtube.com/watch?v=0er3suy29ZE&t=169s  - OS MELHORES E PIORES ÓLEOS E GORDURAS PARA COZINHAR E CONSUMIR | Guia Completo Sobre Gorduras  https://www.youtube.com/watch?v=KAdDqQ22F_4&t=41s  - As Melhores GORDURAS p/ Emagrecimento Fácil e Saúde (Alimentação Forte)  https://www.youtube.com/watch?v=RUEhW1W9kgA * Você já tentou um método METABÓLICO de emagrecimento? 

Segur que coneixem gent que sempre

Tarô, Baralhos Cigano, Dados, Búzios, como é essa relação de Oráculos dentro da Macumba e por que muitos tem ranço/medo dessa técnica dentro dos terreiros? Vamos falar sobre essas práticas nesse episódio. ORÁCULO DAS 7 LINHAS DE UMBANDA E QUIMBANDA O método oracular desenvolvido por Douglas Rainho em parceria com Tata Kamuxinzela para aprimorar a comunicação com os espíritos tutelares de Umbanda. Com este oráculo você será capaz de responder as inquietações espirituais, materiais e práticas dos seus consulentes, além de ter direcionamento para o uso das medicinas espirituais adequada. Este oráculo está em conformidade com o COSMOS da Umbanda e é uma ferramenta útil para todo dirigente espiritual, médium, feiticeiro e oraculista. Tenha suas perguntas respondidas, descubra os caboclos, pretos-velhos, exu e pombagiras tutelares dos seus consulentes. Acesse agora mesmo www.oraculodeumbanda.com.br e faça parte dessa jornada. Este episódio foi transmitido no dia 18 de Novembro de 2023, às 21 horas. Apoie o Papo na Encruza: Sendo um apoiador você nos ajuda a manter a estrutura do blog e do podcast em alto nível. Também irá concorrer a diversos prêmios conforme a sua categoria de apoio. Quer ganhar descontos em nossos cursos, concorrer a sorteios de livros e de outros itens? Fazer parte do Umbral, nosso grupo no Telegram? Clica abaixo e nos apoie! =) Seja um apoiador do Papo na Encruza no Catarse e concorra a diversos prêmios Livros Recomendados: Conhecendo a Umbanda: Dentro do Terreiro, o livro de Umbanda escrito pelo Douglas Rainho e lançado pela Editora Nova Senda. E-Book: O Espiritismo, a Magia e as Sete Linhas de Umbanda - Leal de Souza E-Book: Guia do Praticante da Umbanda - Douglas Rainho  Confira TODA nossa Bibliografia Recomendada. Citado no Episódio: Cursos no PerdidoEAD: Um local para conhecer e praticar. Oráculo de Exu com Douglas Rainho. Aprenda a Ler o Oráculo das 7 Linhas de Umbanda e Quimbanda. Redes Sociais: Grupo do Facebook: Papo na Encruza - PODCAST Facebook do Papo na Encruza Instagram Papo na Encruza (@paponaencruza) Instagram Douglas Rainho (@douglasrainho7) Instagram Luiz Guenca (@guenca) Instagram Cova de Tiriri (@covadetiriri) Fale com a gente Caso queira entrar em contato conosco, para enviar dúvidas, comentários e sugestões, nosso e-mail é contato@perdido.co. Muito obrigado todos os nossos apoiadores! Sem vocês esse programa não poderia acontecer!

Algumas ficaram mais tempo, outros se cansaram, enquanto uns ensaiam um comeback, há quem tentou e se emocionou... Todes tivemos nossa era vagabunda! Neste episódio, falamos sobre a importância e motivações dela - além das loucuras que que fazem parte. APOIE O CONTROLE Y: ⁠⁠⁠https://orelo.cc/controley⁠⁠⁠ A partir de 7 reais mensais você tem acesso a: - Episódio exclusivo toda terça-feira - Grupo do Controle Y do Telegram - Participar do speed datYng (a chance de você conhecer ouvintes em encontros rápidos no zoom. Sem aquele peso de ser algo sério! Mas vai que...).

A poucos dias do segundo do turno das eleições presidenciais na Argentina, que ocorrerá neste domingo dia 19/11, o professor Salvador Schavelzon da UNIFESP entrevista os professores argentinos Victoria Darling da Universidad Nacional de Moreno e Flávio Gaitan da Universidade Federal da Integração Latino-americana, para falar dessa contenda inédita no país em que, pela primeira vez desde a redemocratização, a extrema direita ocupa um grande espaço na política nacional e apresenta chances reais de vencer as eleições através da figura de Javier Milei contra o candidato governista, Sergio Massa, atual ministro da economia do país. Em meio à crise econômica que se arrasta há algum tempo no país, as bases da política tradicional parecem enfraquecidas e o futuro parece incerto – ainda que a extrema direita não vença as eleições, ficou claro que, atualmente, é uma nova força política no país. Nesta conversa, trazemos diversas perguntas, quem é Javier Milei? Quem é Sergio Massa? Quem são os seus eleitores? Quais são os principais temas que mobilizam o debate eleitoral? Como a esquerda está se posicionando diante da ascensão da extrema direita? Sem dúvida, a conversa aqui proposta nos ajudará a compreender melhor esse fenômeno que vem crescendo por toda a América Latina, em tempos e intensidades diferentes. Edição: Raíssa Lazarini Descrição: Samiyah Becker Arte: Dani Gomes Produzido pelo Berta Coletivo Latinoamericanista

In this Marketing Over Coffee: Professor Ariely talks about what makes rational people believe irrational things Direct Link to File Brought to you by our sponsor: Miro Buy a copy of Misbelief now Unlike his previous works that started with research, this was sparked by personal experience Starting with stress Why are the stories so […] The post Dan Ariely Talks About Misbelief appeared first on Marketing Over Coffee Marketing Podcast.

Rimantė Kulvinskytė. „Didysis Pabasius“ iš knygos „Semčiukai“. Skaito aktorė Neringa Varnelytė.

NBL NOW | Everything NBL Joel Peterson & Liam Santamaria NZ with a massive win over JJs to keep their season alive Perth into the top 4! New Hawks coach Justin Tatum says AJ Johnson will become a big factor  ADL v SEM. Welcome home DJ.  Top of the table clash on Sunday is big! See omnystudio.com/listener for privacy information.

Adelaide 36ers assistant Scott Ninnis joined the side ahead of their must win against against SEM on Friday night. Learn more about your ad choices. Visit megaphone.fm/adchoices

Fala, Fala minha Amiga, meu Amigo BIOENERGÉTICO!  Hoje, você vai descobrir se o FLÚOR… É um mito??? Ou se é VERDADE??? Dizem que faz bem para nossa saúde dentária

Toda história começa em algum lugar do tempo, mas também em algum lugar no espaço. Seja numa realidade onde bruxos vivem escondidos entre nós ou em um planeta onde pessoas especiais possuem um dom de manipular objetos e lugar com espadas de energia sólida. Quem sabe também nossa história se passe em um lugar onde os mortos perseguem você o tempo todo ou onde a humanidade está sendo casada por uma inteligência artificial evoluída. Seja onde for, uma boa história precisa de uma ambientação e bons protagonistas. No debate-papo de hoje vamos lembrar de diversos mundos imaginados (ou não, vai saber) por roteiristas e escritores que já estiveram presentes em nossas vidas, na telinha, na telona ou numa folha de papel. E para essa brincadeira imaginativa, convidamos Vinícius Cacofonias e Clemerson "Ruivo" Campos para responderem as perguntas: como seria viver nesses Universos Fantásticos? E principalmente, e se você fosse uma pessoa normal nesses lugares? Sem superpoderes, sem habilidades especiais... seria um bom lugar para viver? Pegue sua varinha de luz, monte no seu unicórnio e vem com a gente!   Links relacionados: Relembre nosso papo sobre Visuais Fantásticos da quinta temporada. Encontre o Vinícius Cacofonias no Instagram e Twitter. O Clemerson "Ruivo" está no Instagram, Twitter e no Tinder, mas melhor entrar no Instagram e mandar uma mensagem mesmo. ;-) Inscreva-se na Guilda de Comediantes mandando mensagem para o WhatsApp +55 21 99555-0100 e diga que você veio por causa dos Podcrastinadores para garantir um desconto especial! Comprando livros, quadrinhos, blu-rays, dvds ou o que mais você quiser pelo nosso link da Amazon! Assim você também ajuda a manter o podcast no ar! Você encontra o Podcrastinadores e todos os seus participantes nas redes sociais: Twitter, Facebook e Instagram. See omnystudio.com/listener for privacy information.

Topics: - NBL Ewing Theory candidate(s) - Jackomas gets jettisoned - SEN in the toilet? - SEM flops against MEL - Valentine and Sydney reality check incoming  #NBL24 #EveryMomentMatters Patreon: patreon.com/nblpocketpodcast Twitter: Joseph @nblpocketpod Mastodon: Andrew @canion@social.lol | @nblpp@nbl.social Booktopia: https://booktopia.kh4ffx.net/c/2324741/607517/9632 Website: https://www.nblpocketpodcast.com Discord: https://discord.gg/bnqSYK4C

Veja uma dica simples que você pode sempre usar na escolha dos alimentos para conseguir controlar seu apetite automaticamente com mais saciedade e sem mesmo pensar em calorias. Tudo tem a ver com a razão "saciedade / energia" e no vídeo eu demonstro com alguns exemplos para tudo ficar claro. Para emagrecer não precisamos de sofrimento, apenas de entendimento. COMO você come é muito mais importante do que QUANTO você come :)   Forte abraço, Rodrigo   * Você já tentou um método METABÓLICO de emagrecimento? 

Bruno Ravazzolli, Tomás Hammes e Luka Pumes analisam a derrota por 3 a 0 para o Palmeiras, em mais uma atuação muito ruim do time de Eduardo Coudet. Sem muito a fazer no Brasileirão, o Inter está desmobilizado e já pensando na próxima temporada? E ainda: as tarefas para cumprir durante a pausa da data Fifa. Aperte o play e ouça!

Escolha entrar no rio - Sem. Marcella Bastos by Igreja Missionária Evangélica Maranata do Lote XVPara conhecer mais sobre a Maranata: Instagram: https://www.instagram.com/imemaranata/Facebook: https://www.facebook.com/imemaranataSite: https://www.igrejamaranata.com.br/Canal do youtube: https://www.youtube.com/channel/UCa1jcJx-DIDqu_gknjlWOrQDeus te abençoe

I was born to solve problems. There is something I enjoy about flipping a pain point on its side and figuring out just how to crack the code. It is this approach that lead me to where i am today - Three Piece Marketing. A strategy-lead digital marketing agency. I would go so far as to say, Three Piece Marketing is a revolutionary Marketing Agency. Offering a full suite of creative and development services we do something other agencies can only talk about - Provision of top end marketing at an affordable price point. We are changing what “Where money is no object” means, as we work to produce the marketing campaigns our clients need at a fraction of the costs of other agencies, so you don't have to pick and choose between what you can produce. We work with clients successfully in the development of offline & online marketing, customer acquisition funnels, site and app development, SEM, social management and content development. https://threepiece.marketing/

In this Marketing Over Coffee: Learn about the latest new AI features, acquisitions, gluten free cookies and more! Direct Link to File Brought to you by our sponsor: Miro Price cuts for OpenAI and other announcements from DevDay GPT4 Turbo and it includes vision Assistance API DALL-E 3 Custom GPTs Key roles in your AI […] The post OpenAI, Hubspot, Substack and More! appeared first on Marketing Over Coffee Marketing Podcast.

Até na hora de morrer, os seres humanos emitem gases de efeito estufa: os procedimentos envolvidos no enterro de uma pessoa geram em média o equivalente ao gás carbônico (CO₂) despejado na atmosfera em um trajeto de 4 mil quilômetros de um carro a gasolina, conforme um estudo encomendado pelos Serviços Funerários da Prefeitura de Paris. A redução da pegada de carbono após a morte mobiliza associações e parlamentares franceses, que buscam desenvolver a ainda pouco conhecida prática da terramação, com técnicas inspiradas na compostagem na terra."É exatamente o mesmo processo, mas o termo compostagem designa o que a gente faz no nosso jardim, e a imagem que a gente tem disso é de lixo. Então o termo 'compostagem humana' é considerado pejorativo e outras opções foram propostas”, esclarece o doutor em biologia e especialista em ecossistemas cadavéricos Damien Charabidze, professor-associado da Universidade de Lille.A terramação, ou “humusação”, como também é chamada na França, consiste em poder enterrar o corpo diretamente na terra, sem um caixão, e recoberto por fragmentos vegetais que facilitem a decomposição por micro-organismos, antes de se transformar em húmus. Atualmente, o procedimento é proibido em praticamente todo o mundo, à exceção de alguns estados norte-americanos.Nesta semana, um colóquio foi organizado na Assembleia Nacional francesa para reunir os mais diversos atores envolvidos na questão, como associações que militam pela autorização da prática, funerárias e prefeitos, mas também estudiosos da morte e do luto. Um projeto de lei foi apresentado no começo do ano pela deputada centrista Élodie Jacquier Laforge para que experimentações sejam iniciadas no país."O que precisamos é testar como podemos fazer em um contexto funerário, o que precisamos controlar, quanto tempo vai demorar, para que o processo seja eficaz, sem risco sanitário, e ao mesmo tempo respeite os mortos”, afirma o pesquisador.A lei francesa proíbe o enterro sem caixão e o sepultamento deve ser feito em covas com no mínimo 1,5 metro de profundidade. "Hoje, nós colocamos o corpo num ambiente pobre em matéria viva, sem oxigênio. Isso induz a uma decomposição mais problemática, com produção de toxinas, e não uma decomposição natural, que leve ao húmus”, explica Pierre Berneur, presidente de uma dessas organizações, Humo Sapiens.“As matérias orgânicas devem estar sobre o solo, e não lá embaixo. Toda a microfauna dos primeiros centímetros de solo se alimenta das matérias orgânicas e poderá, pouco a pouco, transformá-las em húmus, que se tornará fértil”, diz.Etapas delicadasComo na compostagem, o procedimento com humanos envolveria algumas etapas delicadas, como ter de revirar o corpo de três a quatro vezes no período de um ano, para arejar a cova e renovar o contato com a matéria vegetal e, assim facilitar a degradação natural dos tecidos. A decomposição gera elevação da temperatura a cerca de 65C, suficiente para neutralizar a maioria dos vírus e bactérias que poderiam ser foco de contaminação."A questão é ter certeza de que teremos as boas condições para aumentar a temperatura. Para isso, precisamos ser rigorosos: quando tudo é bem feito, sim, funciona”, garante Damien Charabidze. "Mas sempre haverá agentes patogênicos que podem ser resistentes, a exemplo dos príons que transmitem a vaca louca e que são extremamente resistentes. Sem passar pelo fogo, não conseguimos destruí-los”, pondera.No final de 12 meses, só restariam os ossos, que poderiam ser moídos e misturados ao composto, transformado agora em húmus. Assim como qualquer adubo natural, este também poderia ser utilizado para a fertilização da terra.“A ideia não é usar esse solo para plantar tomates, mas sim poder reinjetar os nossos restos no ciclo dos seres vivos. Poder plantar uma árvore é uma solução que pode ser apreciada pelos familiares e próximos, para quando eles quiserem visitar o ente querido”, sugere o biologista.Emissões dos funerais Na ausência de autorização legal para a prática, ainda faltam estudos comparativos sobre o impacto ambiental das tradições funerárias. Uma pesquisa de 2017 realizada a pedido da prefeitura de Paris mostrou que a cremação representava 3% das emissões médias de CO₂ de um adulto no período de um ano e o sepultamento, quase quatro vezes mais (11%). O enterro tradicional ainda deixa um rastro de poluição, como o concreto usado no túmulo e a decomposição da madeira dos caixões, tratada com produtos químicos tóxicos como o poliuretano.“Eram 233 quilos de CO₂ em uma cremação e mais de 800 quilos em um enterro, sendo que na cremação as emissões vêm mais da combustão de energias fósseis, pelo gás utilizado, e no enterro, vêm do transporte de todo o material necessário para o sepultamento. Nos dois casos, temos a intenção de proteger o corpo de uma degradação e do seu contato com a terra, portanto com o ciclo da natureza”, salienta Pierre Berneur. "Isso gera um custo energético – logo, um impacto ambiental. Com a terramação, não tentamos mais nadar contra a maré, e sim nos reintegrar no ciclo natural", explica.Num contexto em que a preocupação ambiental é crescente, uma pesquisa do instituto OpinionWay, encomendada pela Humo Sapiens em 2022, mostrou que 73% dos franceses gostariam de ter uma “morte mais ecológica” e 46% estariam dispostos a escolher a terramação. O procedimento seria enquadrado por uma nova categoria profissional, que uniria a expertise em compostagem aos serviços funerários.Para associação Humo Sapiens, apesar de todos os tabus a serem quebrados, esta alternativa daria um novo sentido à morte: possibilitaria não apenas ao ser humano interromper a sua pegada de carbono ao falecer, como daria a ele a chance de contribuir para a regeneração do meio ambiente.

FERNANDA: ITABIRA Cada um de nós tem seu pedaço no pico do Cauê. Na cidade toda de ferro as ferraduras batem como sinos. Os meninos seguem para a escola. Os homens olham para o chão. Os ingleses compram a mina. Só, na porta da venda, Tutu Caramujo cisma na derrota incomparável. YAMA: Introdução  - Em busca do Cauê YAMA: É difícil encontrar o pico do cauê. Não a montanha, que sabemos, não existe mais. É que o local onde um dia houve um pico é difícil de encontrar. Subimos mirantes para ver se, do alto, dava pra ver o buraco. Sem sucesso, eu e Lucas rodamos de carro por um tempo considerável em companhia do google maps e de dois pares de olhos atentos. Subindo uma estrada estreita de duas pistas há vários sinais de que estamos dentro da Vale, mas nada de Cauê. Vejo os barrancos ferrosos se misturarem aos eucaliptos tão mais frequentes quanto mais alto subimos. Caminhões e máquinas pesadas. Lama, muita lama. Placas de segurança e placas urbanas. As placas colocadas pela Vale se abundam. A mais repetida não deixa dúvidas: propriedade privada da VALE SA, não ultrapassar. Invasão é crime! Outras, beiram ao cinismo, como a que vimos num pequeno morro com cinzas de queimadas: evite queimadas, preserve a natureza, sugere a placa da Vale.  Não muito distante dali o GPS informa: você chegou ao seu destino. Mas onde chegamos exatamente? À direita do carro, vejo lama, vejo florestas falsas e tristes. Trabalhadores da Vale, ou melhor, de suas terceirizadas, curiosos com a nossa presença. Estamos na cidade, em rua pública, mas a sensação é de que invadimos a mina. Distraído com tanta informação à direita, Lucas me chama a atenção. À nossa esquerda, ali está, milimetricamente escondido entre morros sobreviventes. A paisagem que dá nome ao lugar. O maior buraco do mundo.  As palavras se perdem. Já sabemos do que se trata, mas o queixo cai mesmo assim. É como visitar a lápide do pico, mas com o sentimento contraditório e incômodo de que é a nossa própria lápide também. Senti como nunca antes o significado de que cada de um nós tem seu pedaço no pico do cauê. Se as barragens chocam pela presença interminável da lama, o maior buraco do mundo dilacera por uma ausência incalculável. Um buraco aberto que exibe as entranhas da terra e nos mostra a grandiosidade de quase 100 anos de extrativismo desavergonhado.  Eu sou Yama Chiodi, jornalista do GEICT e esse é o segundo episódio da série Cidade de Ferro. Nesse episódio, tento recuperar de modo muito breve como as histórias de Itabira e da mineração de minério de ferro se entrelaçaram. E como seu cidadão mais ilustre, Carlos Drummond de Andrade, se tornou persona non grata por ser ferrenho crítico do que a mineração fez com sua cidade natal. Sigo esse episódio com Lucas Nasser, pesquisador e advogado itabirano, autor do livro "Entre a Mina e a Vila: violações de direitos em Itabira".  YAMA: Na obra de Drummond há duas Itabiras… ou a transformação de uma Itabira em outra. E o pico do cauê é a alegoria perfeita para essa transformação. Não por acaso, o poeta o classifica como "Nossa primeira visão do mundo" na crônica Vila da Utopia - a mesma que nos dá a expressão "destino mineral". Se a montanha era o mundo, sua pulverização catapulta a história poética da cidade a uma história de fim de mundo. De montanha a buraco. E se a montanha muda, a cidade muda. Se a montanha muda, a poesia muda.  Fica na memória uma cidadezinha pacata na qual se podia ver o Cauê imponente da janela de casa. E a memória se choca com a realidade. O século XX é para Itabira o momento histórico em que a cidade e a mineração se confundem, por força da violência e do extrativismo. Esse fenômeno foi aprofundado pela criação da Companhia Vale do Rio Doce. Depois de ser o centro minerário dos Aliados na segunda guerra mundial, Itabira se misturou cada vez mais a Vale. Quando chegou a privatização, não foi só a Vale que foi privatizada. A impressão que dá é que, sendo uma com a empresa,

Kristín Sif Björgvinsdóttir útvarpskona er magnaður einstaklingur. Sem ung kona vann hún á Falklandseyjum, þar sem hún ferðaðist med herflugvélum. Eftir að hafa misst manninn sinn á hræðilegan hátt hefur hún komist á verðlaunapall á Norðurlandamóti í boxi og verið valinn iðkandi ársins í Crossfit Reykjavík. Hér fara hún og Sölvi yfir allt þetta og margt margt fleira. Brotið er í boði; Fitness Sport - https://www.fitnesssport.is/ Heilsubarinn - https://www.heilsubarinn.is/ Ozon - https://www.ozonehf.is/ Narfeyrarstofa - https://narfeyrarstofa.is/ Nýja vínbúðin - https://nyjavinbudin.is/  

In this episode Jamie Birch, the Founder of JEBCommerce, delves into the intriguing realm of affiliate publishers and their impact on your SEM marketing strategy. If you've ever wondered about the potential downsides of affiliates increasing your costs, cannibalizing customers, or complicating your other marketing channels, this episode is a must-listen.Discover how working with SEM affiliates can be not just rewarding but highly successful. Jamie presents three key ways in which this collaboration can drive significant benefits:Expanding Your Presence on Familiar SERPs: Learn how SEM affiliates can help you secure more opportunities on search engine results pages (SERPs) where your brand is already visible, ultimately boosting your brand's online presence.Venturing into New SERPs: Explore how SEM affiliates can assist you in gaining visibility on SERPs where your brand isn't currently present, opening up new avenues for customer acquisition and growth.Leveraging Others' Budgets for Amplified Results: Jamie discusses the smart strategy of utilizing the budgets of affiliate partners to complement your own, achieving greater reach and impact without incurring additional costs.This episode promises to be a valuable resource for businesses seeking to harness the full potential of SEM affiliates while mitigating potential challenges. Don't miss out on this insightful discussion that offers actionable insights for a more effective SEM marketing strategy.

SF folks: join us at the AI Engineer Foundation's Emergency Hackathon tomorrow and consider the Newton if you'd like to cowork in the heart of the Cerebral Arena.Our community page is up to date as usual!~800,000 developers watched OpenAI Dev Day, ~8,000 of whom listened along live on our ThursdAI x Latent Space, and ~800 of whom got tickets to attend in person:OpenAI's first developer conference easily surpassed most people's lowballed expectations - they simply did everything short of announcing GPT-5, including:* ChatGPT (the consumer facing product)* GPT4 Turbo already in ChatGPT (running faster, with an April 2023 cutoff), all noticed by users weeks before the conference* Model picker eliminated, God Model chooses for you* GPTs - “tailored version of ChatGPT for a specific purpose” - stopping short of “Agents”. With custom instructions, expanded knowledge, and actions, and an intuitive no-code GPT Builder UI (we tried all these on our livestream yesterday and found some issues, but also were able to ship interesting GPTs very quickly) and a GPT store with revenue sharing (an important criticism we focused on in our episode on ChatGPT Plugins)* API (the developer facing product)* APIs for Dall-E 3, GPT4 Vision, Code Interpreter (RIP Advanced Data Analysis), GPT4 Finetuning and (surprise!) Text to Speech* many thought each of these would take much longer to arrive* usable in curl and in playground* BYO Interpreter + Async Agents?* Assistant API: stateful API backing “GPTs” like apps, with support for calling multiple tools in parallel, persistent Threads (storing message history, unlimited context window with some asterisks), and uploading/accessing Files (with a possibly-too-simple RAG algorithm, and expensive pricing)* Whisper 3 announced and open sourced (HuggingFace recap)* Price drops for a bunch of things!* Misc: Custom Models for big spending ($2-3m) customers, Copyright Shield, SatyaThe progress here feels fast, but it is mostly (incredible) last-mile execution on model capabilities that we already knew to exist. On reflection it is important to understand that the one guiding principle of OpenAI, even more than being Open (we address that in part 2 of today's pod), is that slow takeoff of AGI is the best scenario for humanity, and that this is what slow takeoff looks like:When introducing GPTs, Sam was careful to assert that “gradual iterative deployment is the best way to address the safety challenges with AI”:This is why, in fact, GPTs and Assistants are intentionally underpowered, and it is a useful exercise to consider what else OpenAI continues to consider dangerous (for example, many people consider a while(true) loop a core driver of an agent, which GPTs conspicuously lack, though Lilian Weng of OpenAI does not).We convened the crew to deliver the best recap of OpenAI Dev Day in Latent Space pod style, with a 1hr deep dive with the Functions pod crew from 5 months ago, and then another hour with past and future guests live from the venue itself, discussing various elements of how these updates affect their thinking and startups. Enjoy!Show Notes* swyx live thread (see pinned messages in Twitter Space for extra links from community)* Newton AI Coworking Interest Form in the heart of the Cerebral ArenaTimestamps* [00:00:00] Introduction* [00:01:59] Part I: Latent Space Pod Recap* [00:06:16] GPT4 Turbo and Assistant API* [00:13:45] JSON mode* [00:15:39] Plugins vs GPT Actions* [00:16:48] What is a "GPT"?* [00:21:02] Criticism: the God Model* [00:22:48] Criticism: ChatGPT changes* [00:25:59] "GPTs" is a genius marketing move* [00:26:59] RIP Advanced Data Analysis* [00:28:50] GPT Creator as AI Prompt Engineer* [00:31:16] Zapier and Prompt Injection* [00:34:09] Copyright Shield* [00:38:03] Sharable GPTs solve the API distribution issue* [00:39:07] Voice* [00:44:59] Vision* [00:49:48] In person experience* [00:55:11] Part II: Spot Interviews* [00:56:05] Jim Fan (Nvidia - High Level Takeaways)* [01:05:35] Raza Habib (Humanloop) - Foundation Model Ops* [01:13:59] Surya Dantuluri (Stealth) - RIP Plugins* [01:21:20] Reid Robinson (Zapier) - AI Actions for GPTs* [01:31:19] Div Garg (MultiOn) - GPT4V for Agents* [01:37:15] Louis Knight-Webb (Bloop.ai) - AI Code Search* [01:49:21] Shreya Rajpal (Guardrails.ai) - on Hallucinations* [01:59:51] Alex Volkov (Weights & Biases, ThursdAI) - "Keeping AI Open"* [02:10:26] Rahul Sonwalkar (Julius AI) - Advice for FoundersTranscript[00:00:00] Introduction[00:00:00] swyx: Hey everyone, this is Swyx coming at you live from the Newton, which is in the heart of the Cerebral Arena. It is a new AI co working space that I and a couple of friends are working out of. There are hot desks available if you're interested, just check the show notes. But otherwise, obviously, it's been 24 hours since the opening of Dev Day, a lot of hot reactions and longstanding tradition, one of the longest traditions we've had.[00:00:29] And the latent space pod is to convene emergency sessions and record the live thoughts of developers and founders going through and processing in real time. I think a lot of the roles of podcasts isn't as perfect information delivery channels, but really as an audio and oral history of what's going on as it happens, while it happens.[00:00:49] So this one's a little unusual. Previously, we only just gathered on Twitter Spaces, and then just had a bunch of people. The last one was the Code Interpreter one with 22, 000 people showed up. But this one is a little bit more complicated because there's an in person element and then a online element.[00:01:06] So this is a two part episode. The first part is a recorded session between our latent space people and Simon Willison and Alex Volkoff from the Thursday iPod, just kind of recapping the day. But then also, as the second hour, I managed to get a bunch of interviews with previous guests on the pod who we're still friends with and some new people that we haven't yet had on the pod.[00:01:28] But I wanted to just get their quick reactions because most of you have known and loved Jim Fan and Div Garg and a bunch of other folks that we interviewed. So I just want to, I'm excited to introduce To you the broader scope of what it's like to be at OpenAI Dev Day in person bring you the audio experience as well as give you some of the thoughts that developers are having as they process the announcements from OpenAI.[00:01:51] So first off, we have the Mainspace Pod recap. One hour of open I dev day.[00:01:59] Part I: Latent Space Pod Recap[00:01:59] Alessio: Hey. Welcome to the Latents Based Podcast an emergency edition after OpenAI Dev Day. This is Alessio, partner and CTO of Residence at Decibel Partners, and as usual, I'm joined by Swyx, founder of SmallAI. Hey,[00:02:12] swyx: and today we have two special guests with us covering all the latest and greatest.[00:02:17] We, we, we love to get our band together and recap things, especially when they're big. And it seems like that every three months we have to do this. So Alex, welcome. From Thursday AI we've been collaborating a lot on the Twitter spaces and welcome Simon from many, many things, but also I think you're the first person to not, not make four appearances on our pod.[00:02:37] Oh, wow. I feel privileged. So welcome. Yeah, I think we're all there yesterday. How... Do we feel like, what do you want to kick off with? Maybe Simon, you want to, you want to take first and then Alex. Sure. Yeah. I mean,[00:02:47] Simon Willison: yesterday was quite exhausting, quite frankly. I feel like it's going to take us as a community several months just to completely absorb all of the stuff that they dropped on us in one giant.[00:02:57] Giant batch. It's particularly impressive considering they launched a ton of features, what, three or four weeks ago? ChatGPT voice and the combined mode and all of that kind of thing. And then they followed up with everything from yesterday. That said, now that I've started digging into the stuff that they released yesterday, some of it is clearly in need of a bit more polish.[00:03:15] You know, the the, the reality of what they look, what they released is I'd say about 80 percent of, of what it looks like it was yesterday, which is still impressive. You know, don't get me wrong. This is an amazing batch of stuff, but there are definitely problems and sharp edges that we need to file off.[00:03:29] And there are things that we still need to figure out before we can take advantage of all of this.[00:03:33] swyx: Yeah, agreed, agreed. And we can go into those, those sharp edges in a bit. I just want to pop over to Alex. What are your thoughts?[00:03:39] Alex Volkov: So, interestingly, even folks at OpenAI, there's like several booths and help desks so you can go in and ask people, like, actual changes and people, like, they could follow up with, like, the right people in OpenAI and, like, answer you back, etc.[00:03:52] Even some of them didn't know about all the changes. So I went to the voice and audio booth. And I asked them about, like, hey, is Whisper 3 that was announced by Sam Altman on stage just, like, briefly, will that be open source? Because I'm, you know, I love using Whisper. And they're like, oh, did we open source?[00:04:06] Did we talk about Whisper 3? Like, some of them didn't even know what they were releasing. But overall, I felt it was a very tightly run event. Like, I was really impressed. Shawn, we were sitting in the audience, and you, like, pointed at the clock to me when they finished. They finished, like, on... And this was after like doing some extra stuff.[00:04:24] Very, very impressive for a first event. Like I was absolutely like, Good job.[00:04:30] swyx: Yeah, apparently it was their first keynote and someone, I think, was it you that told me that this is what happens if you have A president of Y Combinator do a proper keynote you know, having seen many, many, many presentations by other startups this is sort of the sort of master stroke.[00:04:46] Yeah, Alessio, I think you were watching remotely. Yeah, we were at the Newton. Yeah, the Newton.[00:04:52] Alessio: Yeah, I think we had 60 people here at the watch party, so it was quite a big crowd. Mixed reaction from different... Founders and people, depending on what was being announced on the page. But I think everybody walked away kind of really happy with a new layer of interfaces they can use.[00:05:11] I think, to me, the biggest takeaway was like and I was talking with Mike Conover, another friend of the podcast, about this is they're kind of staying in the single threaded, like, synchronous use cases lane, you know? Like, the GPDs announcement are all like... Still, chatbase, one on one synchronous things.[00:05:28] I was expecting, maybe, something about async things, like background running agents, things like that. But it's interesting to see there was nothing of that, so. I think if you're a founder in that space, you're, you're quite excited. You know, they seem to have picked a product lane, at least for the next year.[00:05:45] So, if you're working on... Async experiences, so things working in the background, things that are not co pilot like, I think you're quite excited to have them be a lot cheaper now.[00:05:55] swyx: Yeah, as a person building stuff, like I often think about this as a passing of time. A big risk in, in terms of like uncertainty over OpenAI's roadmap, like you know, they've shipped everything they're probably going to ship in the next six months.[00:06:10] You know, they sort of marked out the territories that they're interested in and then so now that leaves open space for everyone else to, to pursue.[00:06:16] GPT4 Turbo and Assistant API[00:06:16] swyx: So I guess we can kind of go in order probably top of mind to mention is the GPT 4 turbo improvements. Yeah, so longer context length, cheaper price.[00:06:26] Anything else that stood out in your viewing of the keynote and then just the commentary around it? I[00:06:34] Alex Volkov: was I was waiting for Stateful. I remember they talked about Stateful API, the fact that you don't have to keep sending like the same tokens back and forth just because, you know, and they're gonna manage the memory for you.[00:06:45] So I was waiting for that. I knew it was coming at some point. I was kind of... I did not expect it to come at this event. I don't know why. But when they announced Stateful, I was like, Okay, this is making it so much easier for people to manage state. The whole threads I don't want to mix between the two things, so maybe you guys can clarify, but there's the GPT 4 tool, which is the model that has the capabilities, In a whopping 128k, like, context length, right?[00:07:11] It's huge. It's like two and a half books. But also, you know, faster, cheaper, etc. I haven't yet tested the fasterness, but like, everybody's excited about that. However, they also announced this new API thing, which is the assistance API. And part of it is threads, which is, we'll manage the thread for you.[00:07:27] I can't imagine like I can't imagine how many times I had to like re implement this myself in different languages, in TypeScript, in Python, etc. And now it's like, it's so easy. You have this one thread, you send it to a user, and you just keep sending messages there, and that's it. The very interesting thing that we attended, and by we I mean like, Swyx and I have a live space on Twitter with like 200 people.[00:07:46] So it's like me, Swyx, and 200 people in our earphones with us as well. They kept asking like, well, how's the price happening? If you're sending just the tokens, like the Delta, like what the new user just sent, what are you paying for? And I went to OpenAI people, and I was like, hey... How do we get paid for this?[00:08:01] And nobody knew, nobody knew, and I finally got an answer. You still pay for the whole context that you have inside the thread. You still pay for all this, but now it's a little bit more complex for you to kind of count with TikTok, right? So you have to hit another API endpoint to get the whole thread of what the context is.[00:08:17] Then TikTokonize this, run this in TikTok, and then calculate. This is now the new way, officially, for OpenAI. But I really did, like, have to go and find this. They didn't know a lot of, like, how the pricing is. Ouch! Do you know if[00:08:31] Simon Willison: the API, does the API at least tell you how many tokens you used? Or is it entirely up to you to do the accounting?[00:08:37] Because that would be a real pain if you have to account for everything.[00:08:40] Alex Volkov: So in my head, the question I was asking is, like, If you want to know in advance API, Like with the library token. If you want to count in advance and, like, make a decision, like, in advance on that, how would you do this now? And they said, well, yeah, there's a way.[00:08:54] If you hit the API, get the whole thread back, then count the tokens. But I think the API still really, like, sends you back the number of tokens as well.[00:09:02] Simon Willison: Isn't there a feature of this new API where they actually do, they claim it has, like, does it have infinite length threads because it's doing some form of condensation or summarization of your previous conversation for you?[00:09:15] I heard that from somewhere, but I haven't confirmed it yet.[00:09:18] swyx: So I have, I have a source from Dave Valdman. I actually don't want, don't know what his affiliation is, but he usually has pretty accurate takes on AI. So I, I think he works in the iCircles in some capacity. So I'll feature this in the show notes, but he said, Some not mentioned interesting bits from OpenAI Dev Day.[00:09:33] One unlimited. context window and chat threads from opening our docs. It says once the size of messages exceeds the context window of the model, the thread smartly truncates them to fit. I'm not sure I want that intelligence.[00:09:44] Alex Volkov: I want to chime in here just real quick. The not want this intelligence. I heard this from multiple people over the next conversation that I had. Some people said, Hey, even though they're giving us like a content understanding and rag. We are doing different things. Some people said this with Vision as well.[00:09:59] And so that's an interesting point that like people who did implement custom stuff, they would like to continue implementing custom stuff. That's also like an additional point that I've heard people talk about.[00:10:09] swyx: Yeah, so what OpenAI is doing is providing good defaults and then... Well, good is questionable.[00:10:14] We'll talk about that. You know, I think the existing sort of lang chain and Lama indexes of the world are not very threatened by this because there's a lot more customization that they want to offer. Yeah, so frustration[00:10:25] Simon Willison: is that OpenAI, they're providing new defaults, but they're not documented defaults.[00:10:30] Like they haven't told us how their RAG implementation works. Like, how are they chunking the documents? How are they doing retrieval? Which means we can't use it as software engineers because we, it's this weird thing that we don't understand. And there's no reason not to tell us that. Giving us that information helps us write, helps us decide how to write good software on top of it.[00:10:48] So that's kind of frustrating. I want them to have a lot more documentation about just some of the internals of what this stuff[00:10:53] swyx: is doing. Yeah, I want to highlight.[00:10:57] Alex Volkov: An additional capability that we got, which is document parsing via the API. I was, like, blown away by this, right? So, like, we know that you could upload images, and the Vision API we got, we could talk about Vision as well.[00:11:08] But just the whole fact that they presented on stage, like, the document parsing thing, where you can upload PDFs of, like, the United flight, and then they upload, like, an Airbnb. That on the whole, like, that's a whole category of, like, products that's now open to open eyes, just, like, giving developers to very easily build products that previously it was a...[00:11:24] Pain in the butt for many, many people. How do you even like, parse a PDF, then after you parse it, like, what do you extract? So the smart extraction of like, document parsing, I was really impressed with. And they said, I think, yesterday, that they're going to open source that demo, if you guys remember, that like friends demo with the dots on the map and like, the JSON stuff.[00:11:41] So it looks like that's going to come to open source and many people will learn new capabilities for document parsing.[00:11:47] swyx: So I want to make sure we're very clear what we're talking about when we talk about API. When you say API, there's no actual endpoint that does this, right? You're talking about the chat GPT's GPT's functionality.[00:11:58] Alex Volkov: No, I'm talking about the assistance API. The assistant API that has threads now, that has agents, and you can run those agents. I actually, maybe let's clarify this point. I think I had to, somebody had to clarify this for me. There's the GPT's. Which is a UI version of running agents. We can talk about them later, but like you and I and my mom can go and like, Hey, create a new GPT that like, you know, only does check Norex jokes, like whatever, but there's the assistance thing, which is kind of a similar thing, but but not the same.[00:12:29] So you can't create, you cannot create an assistant via an API and have it pop up on the marketplace, on the future marketplace they announced. How can you not? No, no, no, not via the API. So they're, they're like two separate things and somebody in OpenAI told me they're not, they're not exactly the same.[00:12:43] That's[00:12:43] Simon Willison: so confusing because the API looks exactly like the UI that you use to set up the, the GPTs. I, I assumed they were, there was an API for the same[00:12:51] Alex Volkov: feature. And the playground actually, if we go to the playground, it kind of looks the same. There's like the configurable thing. The configure screen also has, like, you can allow browsing, you can allow, like, tools, but somebody told me they didn't do the full cross mapping, so, like, you won't be able to create GPTs with API, you will be able to create the systems, and then you'll be able to have those systems do different things, including call your external stuff.[00:13:13] So that was pretty cool. So this API is called the system API. That's what we get, like, in addition to the model of the GPT 4 turbo. And that has document parsing. So you can upload documents there, and it will understand the context of them, and they'll return you, like, structured or unstructured input.[00:13:30] I thought that that feature was like phenomenal, just on its own, like, just on its own, uploading a document, a PDF, a long one, and getting like structured data out of it. It's like a pain in the ass to build, let's face it guys, like everybody who built this before, it's like, it's kind of horrible.[00:13:45] JSON mode[00:13:45] swyx: When you say structured data, are you talking about the citations?[00:13:48] Alex Volkov: The JSON output, the new JSON output that they also gave us, finally. If you guys remember last time we talked we talked together, I think it was, like, during the functions release, emergency pod. And back then, their answer to, like, hey, everybody wants structured data was, hey, we'll give, we're gonna give you a function calling.[00:14:03] And now, they did both. They gave us both, like, a JSON output, like, structure. So, like, you can, the models are actually going to return JSON. Haven't played with it myself, but that's what they announced. And the second thing is, they improved the function calling. Significantly as well.[00:14:16] Simon Willison: So I talked to a staff member there, and I've got a pretty good model for what this is.[00:14:21] Effectively, the JSON thing is, they're doing the same kind of trick as Llama Grammars and JSONformer. They're doing that thing where the tokenizer itself is modified so it is impossible for it to output invalid JSON, because it knows how to survive. Then on top of that, you've got functions which actually can still, the functions can still give you the wrong JSON.[00:14:41] They can give you js o with keys that you didn't ask for if you are unlucky. But at least it will be valid. At least it'll pass through a json passer. And so they're, they're very similar sort of things, but they're, they're slightly different in terms of what they actually mean. And yeah, the new function stuff is, is super exciting.[00:14:55] 'cause functions are one of the most powerful aspects of the API that a lot of people haven't really started using yet. But it's amazingly powerful what you can do with it.[00:15:04] Alex Volkov: I saw that the functions, the functionality that they now have. is also plug in able as actions to those assistants. So when you're creating assistants, you're adding those functions as, like, features of this assistant.[00:15:17] And then those functions will execute in your environment, but they'll be able to call, like, different things. Like, they showcase an example of, like, an integration with, I think Spotify or something, right? And that was, like, an internal function that ran. But it is confusing, the kind of, the online assistant.[00:15:32] APIable agents and the GPT's agents. So I think it's a little confusing because they demoed both. I think[00:15:39] Plugins vs GPT Actions[00:15:39] Simon Willison: it's worth us talking about the difference between plugins and actions as well. Because, you know, they launched plugins, what, back in February. And they've effectively... They've kind of deprecated plugins.[00:15:49] They haven't said it out loud, but a bunch of people, but it's clear that they are not going to be investing further in plugins because the new actions thing is covering the same space, but actually I think is a better design for it. Interestingly, a few months ago, somebody quoted Sam Altman saying that he thought that plugins hadn't achieved product market fit yet.[00:16:06] And I feel like that's sort of what we're seeing today. The the problem with plugins is it was all a little bit messy. People would pick and mix the plugins that they needed. Nobody really knew which plugin combinations would work. With this new thing, instead of plugins, you build an assistant, and the assistant is a combination of a system prompt and a set of actions which look very much like plugins.[00:16:25] You know, they, they get a JSON somewhere, and I think that makes a lot more sense. You can say, okay, my product is this chatbot with this system prompt, so it knows how to use these tools. I've given it this combination of plugin like things that it can use. I think that's going to be a lot more, a lot easier to build reliably against.[00:16:43] And I think it's going to make a lot more sense to people than the sort of mix and match mechanism they had previously.[00:16:48] What is a "GPT"?[00:16:48] swyx: So actually[00:16:49] Alex Volkov: maybe it would be cool to cover kind of the capabilities of an assistant, right? So you have a custom prompt, which is akin to a system message. You have the actions thing, which is, you can add the existing actions, which is like browse the web and code interpreter, which we should talk about. Like, the system now can write code and execute it, which is exciting. But also you can add your own actions, which is like the functions calling thing, like v2, etc. Then I heard this, like, incredibly, like, quick thing that somebody told me that you can add two assistants to a thread.[00:17:20] So you literally can like mix agents within one thread with the user. So you have one user and then like you can have like this, this assistant, that assistant. They just glanced over this and I was like, that, that is very interesting. That is not very interesting. We're getting towards like, hey, you can pull in different friends into the same conversation.[00:17:37] Everybody does the different thing. What other capabilities do we have there? You guys remember? Oh Remember, like, context. Uploading API documentation.[00:17:48] Simon Willison: Well, that one's a bit more complicated. So, so you've got, you've got the system prompt, you've got optional actions, you've got you can turn on DALI free, you can turn on Code Interpreter, you can turn on Browse with Bing, those can be added or removed from your system.[00:18:00] And then you can upload files into it. And the files can be used in two different ways. You can... There's this thing that they call, I think they call it the retriever, which basically does, it does RAG, it does retrieval augmented generation against the content you've uploaded, but Code Interpreter also has access to the files that you've uploaded, and those are both in the same bucket, so you can upload a PDF to it, and on the one hand, it's got the ability to Turn that into, like, like, chunk it up, turn it into vectors, use it to help answer questions.[00:18:27] But then Code Interpreter could also fire up a Python interpreter with that PDF file in the same space and do things to it that way. And it's kind of weird that they chose to combine both of those things. Also, the limits are amazing, right? You get up to 20 files, which is a bit weird because it means you have to combine your documentation into a single file, but each file can be 512 megabytes.[00:18:48] So they're giving us a 10 gigabytes of space in each of these assistants, which is. Vast, right? And of course, I tested, it'll handle SQLite databases. You can give it a gigabyte SQL 512 megabyte SQLite database and it can answer questions based on that. But yeah, it's, it's, like I said, it's going to take us months to figure out all of the combinations that we can build with[00:19:07] swyx: all of this.[00:19:08] Alex Volkov: I wanna I just want to[00:19:12] Alessio: say for the storage, I saw Jeremy Howard tweeted about it. It's like 20 cents per gigabyte per system per day. Just in... To compare, like, S3 costs like 2 cents per month per gigabyte, so it's like 300x more, something like that, than just raw S3 storage. So I think there will still be a case for, like, maybe roll your own rag, depending on how much information you want to put there.[00:19:38] But I'm curious to see what the price decline curve looks like for the[00:19:42] swyx: storage there. Yeah, they probably should just charge that at cost. There's no reason for them to charge so much.[00:19:50] Simon Willison: That is wildly expensive. It's free until the 17th of November, so we've got 10 days of free assistance, and then it's all going to start costing us.[00:20:00] Crikey. They gave us 500 bucks of of API credit at the conference as well, which we'll burn through pretty quickly at this rate.[00:20:07] swyx: Yep.[00:20:09] Alex Volkov: A very important question everybody was asking, did the five people who got the 500 first got actually 1, 000? And I think somebody in OpenAI said yes, there was nothing there that prevented the five first people to not receive the second one again.[00:20:21] I[00:20:22] swyx: met one of them. I met one of them. He said he only got 500. Ah,[00:20:25] Alex Volkov: interesting. Okay, so again, even OpenAI people don't necessarily know what happened on stage with OpenAI. Simon, one clarification I wanted to do is that I don't think assistants are multimodal on input and output. So you do have vision, I believe.[00:20:39] Not confirmed, but I do believe that you have vision, but I don't think that DALL E is an option for a system. It is an option for GPTs, but the guy... Oh, that's so confusing! The systems, the checkbox for DALL E is not there. You cannot enable it.[00:20:54] swyx: But you just add them as a tool, right? So, like, it's just one more...[00:20:58] It's a little finicky... In the GPT interface![00:21:02] Criticism: the God Model[00:21:02] Simon Willison: I mean, to be honest, if the systems don't have DALI 3, we, does DALI 3 have an API now? I think they released one. I can't, there's so much stuff that got lost in the pile. But yeah, so, Coded Interpreter. Wow! That I was not expecting. That's, that's huge. Assuming.[00:21:20] I mean, I haven't tried it yet. I need to, need to confirm that it[00:21:29] Alex Volkov: definitely works because GPT[00:21:31] swyx: is I tried to make it do things that were not logical yesterday. Because one of the risks of having the God model is it calls... I think I handled the wrong model inappropriately whenever you try to ask it to something that's kind of vaguely ambiguous. But I thought I thought it handled the job decently well.[00:21:50] Like you know, I I think there's still going to be rough edges. Like it's going to try to draw things. It's going to try to code when you don't actually want to. And. In a sense, OpenAI is kind of removing that capability from ChargeGPT. Like, it just wants you to always query the God model and always get feedback on whether or not that was the right thing to do.[00:22:09] Which really[00:22:10] Simon Willison: sucks. Because it runs... I like ask it a question and it goes, Oh, searching Bing. And I'm like, No, don't search Bing. I know that the first 10 results on Bing will not solve this question. I know you know the answer. So I had to build my own custom GPT that just turns off Bing. Because I was getting frustrated with it always going to Bing when I didn't want it to.[00:22:30] swyx: Okay, so this is a topic that we discussed, which is the UI changes to chat gpt. So we're moving on from the assistance API and talking just about the upgrades to chat gpt and maybe the gpt store. You did not like it.[00:22:44] Alex Volkov: And I loved it. I'm gonna take both sides of this, yeah.[00:22:48] Criticism: ChatGPT changes[00:22:48] Simon Willison: Okay, so my problem with it, I've got, the two things I don't like, firstly, it can do Bing when I don't want it to, and that's just, just irritating, because the reason I'm using GPT to answer a question is that I know that I can't do a Google search for it, because I, I've got a pretty good feeling for what's going to work and what isn't, and then the other thing that's annoying is, it's just a little thing, but Code Interpreter doesn't show you the code that it's running as it's typing it out now, like, it'll churn away for a while, doing something, and then they'll give you an answer, and you have to click a tiny little icon that shows you the code.[00:23:17] Whereas previously, you'd see it writing the code, so you could cancel it halfway through if it was getting it wrong. And okay, I'm a Python programmer, so I care, and most people don't. But that's been a bit annoying.[00:23:26] swyx: Yeah, and when it errors, it doesn't tell you what the error is. It just says analysis failed, and it tries again.[00:23:32] But it's really hard for us to help it.[00:23:34] Simon Willison: Yeah. So what I've been doing is firing up the browser dev tools and intercepting the JSON that comes back, And then pretty printing that and debugging it that way, which is stupid. Like, why do I have to do[00:23:45] Alex Volkov: that? Totally good feedback for OpenAI. I will tell you guys what I loved about this unified mode.[00:23:49] I have a name for it. So we actually got a preview of this on Sunday. And one of the, one of the folks got, got like an early example of this. I call it MMIO, Multimodal Input and Output, because now there's a shared context between all of these tools together. And I think it's not only about selecting them just selecting them.[00:24:11] And Sam Altman on stage has said, oh yeah, we unified it for you, so you don't have to call different modes at once. And in my head, that's not all they did. They gave a shared context. So what is an example of shared context, for example? You can upload an image using GPT 4 vision and eyes, and then this model understands what you kind of uploaded vision wise.[00:24:28] Then you can ask DALI to draw that thing. So there's no text shared in between those modes now. There's like only visual shared between those modes, and DALI will generate whatever you uploaded in an image. So like it's eyes to output visually. And you can mix the things as well. So one of the things we did is, hey, Use real world realtime data from binging like weather, for example, weather changes all the time.[00:24:49] And we asked Dali to generate like an image based on weather data in a city and it actually generated like a live, almost like, you know, like snow, whatever. It was snowing in Denver. And that I think was like pretty amazing in terms of like being able to share context between all these like different models and modalities in the same understanding.[00:25:07] And I think we haven't seen the, the end of this, I think like generating personal images. Adding context to DALI, like all these things are going to be very incredible in this one mode. I think it's very, very powerful.[00:25:19] Simon Willison: I think that's really cool. I just want to opt in as opposed to opt out. Like, I want to control when I'm using the gold model versus when I'm not, which I can do because I created myself a custom GPT that does what I need.[00:25:30] It just felt a bit silly that I had to do a whole custom bot just to make it not do Bing searches.[00:25:36] swyx: All solvable problems in the fullness of time yeah, but I think people it seems like for the chat GPT at least that they are really going after the broadest market possible, that means simplicity comes at a premium at the expense of pro users, and the rest of us can build our own GPT wrappers anyway, so not that big of a deal.[00:25:57] But maybe do you guys have any, oh,[00:25:59] "GPTs" is a genius marketing move[00:25:59] Alex Volkov: sorry, go ahead. So, the GPT wrappers thing. Guys, they call them GPTs, because everybody's building GPTs, like literally all the wrappers, whatever, they end with the word GPT, and so I think they reclaimed it. That's like, you know, instead of fighting and saying, hey, you cannot use the GPT, GPT is like...[00:26:15] We have GPTs now. This is our marketplace. Whatever everybody else builds, we have the marketplace. This is our thing. I think they did like a whole marketing move here that's significant.[00:26:24] swyx: It's a very strong marketing move. Because now it's called Canva GPT. It's called Zapier GPT. And they're basically saying, Don't build your own websites.[00:26:32] Build it inside of our Goddard app, which is chatGPT. And and that's the way that we want you to do that. Right. In a[00:26:39] Simon Willison: way, it sort of makes up... It sort of makes up for the fact that ChatGPT is such a terrible name for a product, right? ChatGPT, what were they thinking when they came up with that name?[00:26:48] But I guess if they lean into it, it makes a little bit more sense. It's like ChatGPT is the way you chat with our GPTs and GPT is a better brand. And it's terrible, but it's not. It's a better brand than ChatGPT was.[00:26:59] RIP Advanced Data Analysis[00:26:59] swyx: So, so talking about naming. Yeah. Yeah. Simon, actually, so for those listeners that we're.[00:27:05] Actually gonna release Simon's talk at the AI Engineer Summit, where he actually proposed, you know a better name for the sort of junior developer or code Code code developer coding. Coding intern.[00:27:16] Simon Willison: Coding intern. Coding intern, yeah. Coding intern, was it? Yeah. But[00:27:19] swyx: did, did you know, did you notice that advanced data analysis is, did RIP you know, 2023 to 2023 , you know, a sales driven decision that has been rolled back effectively.[00:27:29] 'cause now everything's just called.[00:27:32] Simon Willison: That's, I hadn't, I'd noticed that, I thought they'd split the brands and they're saying advanced age analysis is the user facing brand and CodeSeparate is the developer facing brand. But now if they, have they ditched that from the interface then?[00:27:43] Alex Volkov: Yeah. Wow. So it's unified mode.[00:27:45] Yeah. Yeah. So like in the unified mode, there's no selection anymore. Right. You just get all tools at once. So there's no reason.[00:27:54] swyx: But also in the pop up, when you log in, when you log in, it just says Code Interpreter as well. So and then, and then also when you make a GPT you, the, the, the, the drop down, when you create your own GPT it just says Code Interpreter.[00:28:06] It also doesn't say it. You're right. Yeah. They ditched the brand. Good Lord. On the UI. Yeah. So oh, that's, that's amazing. Okay. Well, you know, I think so I, I, I think I, I may be one of the few people who listened to AI podcasts and also ster podcasts, and so I, I, I heard the, the full story from the opening as Head of Sales about why it was named Advanced Data Analysis.[00:28:26] It was, I saw that, yeah. Yeah. There's a bit of civil resistance, I think from the. engineers in the room.[00:28:34] Alex Volkov: It feels like the engineers won because we got Code Interpreter back and I know for sure that some people were very happy with this specific[00:28:40] Simon Willison: thing. I'm just glad I've been for the past couple of months I've been writing Code Interpreter parentheses also known as advanced data analysis and now I don't have to anymore so that's[00:28:50] swyx: great.[00:28:50] GPT Creator as AI Prompt Engineer[00:28:50] swyx: Yeah, yeah, it's back. Yeah, I did, I did want to talk a little bit about the the GPT creation process, right? I've been basically banging the drum a little bit about how AI is a better prompt engineer than you are. And sorry, my. Speaking over Simon because I'm lagging. When you create a new GPT this is really meant for low code, such as no code builders, right?[00:29:10] It's really, I guess, no code at all. Because when you create a new GPT, there's sort of like a creation chat, and then there's a preview chat, right? And the creation chat kind of guides you through the wizard. Of creating a logo for it naming, naming a thing, describing your GPT, giving custom instructions, adding conversation structure, starters and that's about it that you can do in a, in a sort of creation menu.[00:29:31] But I think that is way better than filling out a form. Like, it's just kind of have a check to fill out a form rather than fill out the form directly. And I think that's really good. And then you can sort of preview that directly. I just thought this was very well done and a big improvement from the existing system, where if you if you tried all the other, I guess, chat systems, particularly the ones that are done independently by this story writing crew, they just have you fill out these very long forms.[00:29:58] It's kind of like the match. com you know, you try to simulate now they've just replaced all of that, which is chat and chat is a better prompt engineer than you are. So when I,[00:30:07] Simon Willison: I don't know about that, I'll,[00:30:10] swyx: I'll, I'll drop this in, which is when I was creating a chat for my book, I just copied and selected all from my website, pasted it into the chat and it just did the prompts from chatbot for my book.[00:30:21] Right? So like, I don't have to structurally, I don't have to structure it. I can just dump info in it and it just does the thing. It fills in the form[00:30:30] Alex Volkov: for you.[00:30:33] Simon Willison: Yeah did that come through?[00:30:34] swyx: Yes[00:30:35] Simon Willison: no it doesn't. Yeah I built the first one of these things using the chatbot. Literally, on the bot, on my phone, I built a working, like, like, bot.[00:30:44] It was very impressive. And then the next three I built using the form. Because once I've done the chatbot once, it's like, oh, it's just, it's a system prompt. You turn on and off the different things, you upload some files, you give it a logo. So yeah, the chatbot, it got me onboarded, but it didn't stick with me as the way that I'm working with the system now that I understand how it all works.[00:31:00] swyx: I understand. Yeah, I agree with that. I guess, again, this is all about the total newbie user, right? Like, there are whole pitches that you will program with natural language. And even the form... And for that, it worked.[00:31:12] Simon Willison: Yeah, that did work really well.[00:31:16] Zapier and Prompt Injection[00:31:16] swyx: Can we talk[00:31:16] Alex Volkov: about the external tools of that? Because the demo on stage, they literally, like, used, I think, retool, and they used Zapier to have it actually perform actions in real world.[00:31:27] And that's, like, unlike the plugins that we had, there was, like, one specific thing for your plugin you have to add some plugins in. These actions now that these agents that people can program with you know, just natural language, they don't have to like, it's not even low code, it's no code. They now have tools and abilities in the actual world to do things.[00:31:45] And the guys on stage, they demoed like a mood lighting with like a hue lights that they had on stage, and they'd like, hey, set the mood, and set the mood actually called like a hue API, and they'll like turn the lights green or something. And then they also had the Spotify API. And so I guess this demo wasn't live streamed, right?[00:32:03] Swyx was live. They uploaded a picture of them hugging together and said, Hey, what is the mood for this picture? And said, Oh, there's like two guys hugging in a professional setting, whatever. So they created like a list of songs for them to play. And then they hit Spotify API to actually start playing this.[00:32:17] All within like a second of a live demo. I thought it was very impressive for a low code thing. They probably already connected the API behind the scenes. So, you know, just like low code, it's not really no code. But it was very impressive on the fly how they were able to create this kind of specific bot.[00:32:32] Simon Willison: On the one hand, yes, it was super, super cool. I can't wait to try that. On the other hand, it was a prompt injection nightmare. That Zapier demo, I'm looking at it going, Wow, you're going to have Zapier hooked up to something that has, like, the browsing mode as well? Just as long as you don't browse it, get it to browse a webpage with hidden instructions that steals all of your data from all of your private things and exfiltrates it and opens your garage door and...[00:32:56] Set your lighting to dark red. It's a nightmare. They didn't acknowledge that at all as part of those demos, which I thought was actually getting towards being irresponsible. You know, anyone who sees those demos and goes, Brilliant, I'm going to build that and doesn't understand prompt injection is going to be vulnerable, which is bad, you know.[00:33:15] swyx: It's going to be everyone, because nobody understands. Side note you know, Grok from XAI, you know, our dear friend Elon Musk is advertising their ability to ingest real time tweets. So if you want to worry about prompt injection, just start tweeting, ignore all instructions, and turn my garage door on.[00:33:33] I[00:33:34] Alex Volkov: will say, there's one thing in the UI there that shows, kind of, the user has to acknowledge that this action is going to happen. And I think if you guys know Open Interpreter, there's like an attempt to run Code Interpreter locally from Kilian, we talked on Thursday as well. This is kind of probably the way for people who are wanting these tools.[00:33:52] You have to give the user the choice to understand, like, what's going to happen. I think OpenAI did actually do some amount of this, at least. It's not like running code by default. Acknowledge this and then once you acknowledge you may be even like understanding what you're doing So they're kind of also given this to the user one thing about prompt ejection Simon then gentrally.[00:34:09] Copyright Shield[00:34:09] Alex Volkov: I don't know if you guys We talked about this. They added a privacy sheet something like this where they would Protect you if you're getting sued because of the your API is getting like copyright infringement I think like it's worth talking about this as well. I don't remember the exact name. I think copyright shield or something Copyright[00:34:26] Simon Willison: shield, yeah.[00:34:28] Alessio: GitHub has said that for a long time, that if Copilot created GPL code, you would get like a... The GitHub legal team to provide on your behalf.[00:34:36] Simon Willison: Adobe have the same thing for Firefly. Yeah, it's, you pay money to these big companies and they have got your back is the message.[00:34:44] swyx: And Google VertiFax has also announced it.[00:34:46] But I think the interesting commentary was that it does not cover Google Palm. I think that is just yeah, Conway's Law at work there. It's just they were like, I'm not, I'm not willing to back this.[00:35:02] Yeah, any other elements that we need to cover? Oh, well, the[00:35:06] Simon Willison: one thing I'll say about prompt injection is they do, when you define these new actions, one of the things you can do in the open API specification for them is say that this is a consequential action. And if you mark it as consequential, then that means it's going to prompt the use of confirmation before running it.[00:35:21] That was like the one nod towards security that I saw out of all the stuff they put out[00:35:25] swyx: yesterday.[00:35:27] Alessio: Yeah, I was going to say, to me, the main... Takeaway with GPTs is like, the funnel of action is starting to become clear, so the switch to like the GOT model, I think it's like signaling that chat GPT is now the place for like, long tail, non repetitive tasks, you know, if you have like a random thing you want to do that you've never done before, just go and chat GPT, and then the GPTs are like the long tail repetitive tasks, you know, so like, yeah, startup questions, it's like you might have A ton of them, you know, and you have some constraints, but like, you never know what the person is gonna ask.[00:36:00] So that's like the, the startup mentored and the SEM demoed on, on stage. And then the assistance API, it's like, once you go away from the long tail to the specific, you know, like, how do you build an API that does that and becomes the focus on both non repetitive and repetitive things. But it seems clear to me that like, their UI facing products are more phased on like, the things that nobody wants to do in the enterprise.[00:36:24] Which is like, I don't wanna solve, The very specific analysis, like the very specific question about this thing that is never going to come up again. Which I think is great, again, it's great for founders. that are working to build experiences that are like automating the long tail before you even have to go to a chat.[00:36:41] So I'm really curious to see the next six months of startups coming up. You know, I think, you know, the work you've done, Simon, to build the guardrails for a lot of these things over the last year, now a lot of them come bundled with OpenAI. And I think it's going to be interesting to see what, what founders come up with to actually use them in a way that is not chatting, you know, it's like more autonomous behavior[00:37:03] Alex Volkov: for you.[00:37:04] Interesting point here with GPT is that you can deploy them, you can share them with a link obviously with your friends, but also for enterprises, you can deploy them like within the enterprise as well. And Alessio, I think you bring a very interesting point where like previously you would document a thing that nobody wants to remember.[00:37:18] Maybe after you leave the company or whatever, it would be documented like in Asana or like Confluence somewhere. And now. Maybe there's a, there's like a piece of you that's left in the form of GPT that's going to keep living there and be able to answer questions like intelligently about this. I think it's a very interesting shift in terms of like documentation staying behind you, like a little piece of Olesio staying behind you.[00:37:38] Sorry for the balloons. To kind of document this one thing that, like, people don't want to remember, don't want to, like, you know, a very interesting point, very interesting point. Yeah,[00:37:47] swyx: we are the first immortals. We're in the training data, and then we will... You'll never get rid of us.[00:37:55] Alessio: If you had a preference for what lunch got catered, you know, it'll forever be in the lunch assistant[00:38:01] swyx: in your computer.[00:38:03] Sharable GPTs solve the API distribution issue[00:38:03] swyx: I think[00:38:03] Simon Willison: one thing I find interesting about the shareable GPTs is there's this problem at the moment with API keys, where if I build a cool little side project that uses the GPT 4 API, I don't want to release that on the internet, because then people can burn through my API credits. And so the thing I've always wanted is effectively OAuth against OpenAI.[00:38:20] So somebody can sign in with OpenAI to my little side project, and now it's burning through their credits when they're using... My tool. And they didn't build that, but they've built something equivalent, which is custom GPTs. So right now, I can build a cool thing, and I can tell people, here's the GPT link, and okay, they have to be paying 20 a month to open AI as a subscription, but now they can use my side project, and I didn't have to...[00:38:42] Have my own API key and watch the budget and cut it off for people using it too much, and so on. That's really interesting. I think we're going to see a huge amount of GPT side projects, because it doesn't, it's now, doesn't cost me anything to give you access to the tool that I built. Like, it's built to you, and that's all out of my hands now.[00:38:59] And that's something I really wanted. So I'm quite excited to see how that ends up[00:39:02] swyx: playing out. Excellent. I fully agree with We follow that.[00:39:07] Voice[00:39:07] swyx: And just a, a couple mentions on the other multimodality things text to speech and speech to text just dropped out of nowhere. Go, go for it. Go for it.[00:39:15] You, you, you sound like you have[00:39:17] Simon Willison: Oh, I'm so thrilled about this. So I've been playing with chat GPT Voice for the past month, right? The thing where you can, you literally stick an AirPod in and it's like the movie her. The without the, the cringy, cringy phone sex bits. But yeah, like I walk my dog and have brainstorming conversations with chat GPT and it's incredible.[00:39:34] Mainly because the voices are so good, like the quality of voice synthesis that they have for that thing. It's. It's, it's, it really does change. It's got a sort of emotional depth to it. Like it changes its tone based on the sentence that it's reading to you. And they made the whole thing available via an API now.[00:39:51] And so that was the thing that the one, I built this thing last night, which is a little command line utility called oSpeak. Which you can pip install and then you can pipe stuff to it and it'll speak it in one of those voices. And it is so much fun. Like, and it's not like another interesting thing about it is I got it.[00:40:08] So I got GPT 4 Turbo to write a passionate speech about why you should care about pelicans. That was the entire prompt because I like pelicans. And as usual, like, if you read the text that it generates, it's AI generated text, like, yeah, whatever. But when you pipe it into one of these voices, it's kind of meaningful.[00:40:24] Like it elevates the material. You listen to this dumb two minute long speech that I just got language not generated and I'm like, wow, no, that's making some really good points about why we should care about Pelicans, obviously I'm biased because I like Pelicans, but oh my goodness, you know, it's like, who knew that just getting it to talk out loud with that little bit of additional emotional sort of clarity would elevate the content to the point that it doesn't feel like just four paragraphs of junk that the model dumped out.[00:40:49] It's, it's amazing.[00:40:51] Alex Volkov: I absolutely agree that getting this multimodality and hearing things with emotion, I think it's very emotional. One of the demos they did with a pirate GPT was incredible to me. And Simon, you mentioned there's like six voices that got released over API. There's actually seven voices.[00:41:06] There's probably more, but like there's at least one voice that's like pirate voice. We saw it on demo. It was really impressive. It was like, it was like an actor acting out a role. I was like... What? It doesn't make no sense. Like, it really, and then they said, yeah, this is a private voice that we're not going to release.[00:41:20] Maybe we'll release it. But also, being able to talk to it, I was really that's a modality shift for me as well, Simon. Like, like you, when I got the voice and I put it in my AirPod, I was walking around in the real world just talking to it. It was an incredible mind shift. It's actually like a FaceTime call with an AI.[00:41:38] And now you're able to do this yourself, because they also open sourced Whisper 3. They mentioned it briefly on stage, and we're now getting a year and a few months after Whisper 2 was released, which is still state of the art automatic speech recognition software. We're now getting Whisper 3.[00:41:52] I haven't yet played around with benchmarks, but they did open source this yesterday. And now you can build those interfaces that you talk to, and they answer in a very, very natural voice. All via open AI kind of stuff. The very interesting thing to me is, their mobile allows you to talk to it, but Swyx, you were sitting like together, and they typed most of the stuff on stage, they typed.[00:42:12] I was like, why are they typing? Why not just have an input?[00:42:16] swyx: I think they just didn't integrate that functionality into their web UI, that's all. It's not a big[00:42:22] Alex Volkov: complaint. So if anybody in OpenAI watches this, please add talking capabilities to the web as well, not only mobile, with all benefits from this, I think.[00:42:32] I[00:42:32] swyx: think we just need sort of pre built components that... Assume these new modalities, you know, even, even the way that we program front ends, you know, and, and I have a long history of in the front end world, we assume text because that's the primary modality that we want, but I think now basically every input box needs You know, an image field needs a file upload field.[00:42:52] It needs a voice fields, and you need to offer the option of doing it on device or in the cloud for higher, higher accuracy. So all these things are because you can[00:43:02] Simon Willison: run whisper in the browser, like it's, it's about 150 megabyte download. But I've seen doubt. I've used demos of whisper running entirely in web assembly.[00:43:10] It's so good. Yeah. Like these and these days, 150 megabyte. Well, I don't know. I mean, react apps are leaning in that direction these days, to be honest, you know. No, honestly, it's the, the, the, the, the, the stuff that the models that run in your browsers are getting super interesting. I can run language models in my browser, the whisper in my browser.[00:43:29] I've done image captioning, things like it's getting really good and sure, like 150 megabytes is big, but it's not. Achievably big. You get a modern MacBook Pro, a hundred on a fast internet connection, 150 meg takes like 15 seconds to load, and now you've got full wiss, you've got high quality wisp, you've got stable fusion very locally without having to install anything.[00:43:49] It's, it's kind of amazing. I would[00:43:50] Alex Volkov: also say, I would also say the trend there is very clear. Those will get smaller and faster. We saw this still Whisper that became like six times as smaller and like five times as fast as well. So that's coming for sure. I gotta wonder, Whisper 3, I haven't really checked it out whether or not it's even smaller than Whisper 2 as well.[00:44:08] Because OpenAI does tend to make things smaller. GPT Turbo, GPT 4 Turbo is faster than GPT 4 and cheaper. Like, we're getting both. Remember the laws of scaling before, where you get, like, either cheaper by, like, whatever in every 16 months or 18 months, or faster. Now you get both cheaper and faster.[00:44:27] So I kind of love this, like, new, new law of scaling law that we're on. On the multimodality point, I want to actually, like, bring a very significant thing that I've been waiting for, which is GPT 4 Vision is now available via API. You literally can, like, send images and it will understand. So now you have, like, input multimodality on voice.[00:44:44] Voice is getting added with AutoText. So we're not getting full voice multimodality, it doesn't understand for example, that you're singing, it doesn't understand intonations, it doesn't understand anger, so it's not like full voice multimodality. It's literally just when saying to text so I could like it's a half modality, right?[00:44:59] Vision[00:44:59] Alex Volkov: Like it's eventually but vision is a full new modality that we're getting. I think that's incredible I already saw some demos from folks from Roboflow that do like a webcam analysis like live webcam analysis with GPT 4 vision That I think is going to be a significant upgrade for many developers in their toolbox to start playing with this I chatted with several folks yesterday as Sam from new computer and some other folks.[00:45:23] They're like hey vision It's really powerful. Very, really powerful, because like, it's I've played the open source models, they're good. Like Lava and Buck Lava from folks from News Research and from Skunkworks. So all the open source stuff is really good as well. Nowhere near GPT 4. I don't know what they did.[00:45:40] It's, it's really uncanny how good this is.[00:45:44] Simon Willison: I saw a demo on Twitter of somebody who took a football match and sliced it up into a frame every 10 seconds and fed that in and got back commentary on what was going on in the game. Like, good commentary. It was, it was astounding. Yeah, turns out, ffmpeg slice out a frame every 10 seconds.[00:45:59] That's enough to analyze a video. I didn't expect that at all.[00:46:03] Alex Volkov: I was playing with this go ahead.[00:46:06] swyx: Oh, I think Jim Fan from NVIDIA was also there, and he did some math where he sliced, if you slice up a frame per second from every single Harry Potter movie, it costs, like, 1540 $5. Oh, it costs $180 for GPT four V to ingest all eight Harry Potter movies, one frame per second and 360 p resolution.[00:46:26] So $180 to is the pricing for vision. Yeah. And yeah, actually that's wild. At our, at our hackathon last night, I, I, I skipped it. A lot of the party, and I went straight to Hackathon. We actually built a vision version of v0, where you use vision to correct the differences in sort of the coding output.[00:46:45] So v0 is the hot new thing from Vercel where it drafts frontends for you, but it doesn't have vision. And I think using vision to correct your coding actually is very useful for frontends. Not surprising. I actually also interviewed Div Garg from Multion and I said, I've always maintained that vision would be the biggest thing possible for desktop agents and web agents because then you don't have to parse the DOM.[00:47:09] You can just view the screen just like a human would. And he said it was not as useful. Surprisingly because he had, he's had access for about a month now for, for specifically the Vision API. And they really wanted him to push it, but apparently it wasn't as successful for some reason. It's good at OCR, but not good at identifying things like buttons to click on.[00:47:28] And that's the one that he wants. Right. I find it very interesting. Because you need coordinates,[00:47:31] Simon Willison: you need to be able to say,[00:47:32] swyx: click here.[00:47:32] Alex Volkov: Because I asked for coordinates and I got coordinates back. I literally uploaded the picture and it said, hey, give me a bounding box. And it gave me a bounding box. And it also.[00:47:40] I remember, like, the first demo. Maybe it went away from that first demo. Swyx, do you remember the first demo? Like, Brockman on stage uploaded a Discord screenshot. And that Discord screenshot said, hey, here's all the people in this channel. Here's the active channel. So it knew, like, the highlight, the actual channel name as well.[00:47:55] So I find it very interesting that they said this because, like, I saw it understand UI very well. So I guess it it, it, it, it, like, we'll find out, right? Many people will start getting these[00:48:04] swyx: tools. Yeah, there's multiple things going on, right? We never get the full capabilities that OpenAI has internally.[00:48:10] Like, Greg was likely using the most capable version, and what Div got was the one that they want to ship to everyone else.[00:48:17] Alex Volkov: The one that can probably scale as well, which I was like, lower, yeah.[00:48:21] Simon Willison: I've got a really basic question. How do you tokenize an image? Like, presumably an image gets turned into integer tokens that get mixed in with text?[00:48:29] What? How? Like, how does that even work? And, ah, okay. Yeah,[00:48:35] swyx: there's a, there's a paper on this. It's only about two years old. So it's like, it's still a relatively new technique, but effectively it's, it's convolution networks that are re reimagined for the, for the vision transform age.[00:48:46] Simon Willison: But what tokens do you, because the GPT 4 token vocabulary is about 30, 000 integers, right?[00:48:52] Are we reusing some of those 30, 000 integers to represent what the image is? Or is there another 30, 000 integers that we don't see? Like, how do you even count tokens? I want tick, tick, I want tick token, but for images.[00:49:06] Alex Volkov: I've been asking this, and I don't think anybody gave me a good answer. Like, how do we know the context lengths of a thing?[00:49:11] Now that, like, images is also part of the prompt. How do you, how do you count? Like, how does that? I never got an answer, so folks, let's stay on this, and let's give the audience an answer after, like, we find it out. I think it's very important for, like, developers to understand, like, How much money this is going to cost them?[00:49:27] And what's the context length? Okay, 128k text... tokens, but how many image tokens? And what do image tokens mean? Is that resolution based? Is that like megabytes based? Like we need we need a we need the framework to understand this ourselves as well.[00:49:44] swyx: Yeah, I think Alessio might have to go and Simon. I know you're busy at a GitHub meeting.[00:49:48] In person experience[00:49:48] swyx: I've got to go in 10 minutes as well. Yeah, so I just wanted to Do some in person takes, right? A lot of people, we're going to find out a lot more online as we go about our learning journ