Forking Paths: Opus 5 vs. OpenAI Voices  🔗 **Source:** [Forking Paths: Opus 5 vs. OpenAI Voices](https://share.snipd.com/episode/3960c86c-8601-4a2c-b537-b18a2d928bc5) ## Highlights - **Using Claude As A Multimodal Control Panel** - Jaeden Schafer used Claude plus AI box to generate and localize 300 podcast covers by making 12 base images and swapping text for each language automatically. - Claude wrote prompts, pulled images via AI box MCP, and replaced fonts/text across Mandarin, Korean and other scripts, saving time and credits. Transcript: Jaeden Schafer So we're going to get into that. But first, my absolute favorite AI tool I've been using this week allows you to generate images and audio and video right inside of Claude who you know only does text and reason and I basically Use Claude as my control panel for everything I do I have two Claude max $200 a month subscriptions and I burn through all of the tokens for both of those because I have a billion projects Going always all at once and this thing is a workhorse now the problem with it is it doesn't generate images like chat GPT, it doesn't generate video like Google, and it doesn't do audio Like 11 labs. So I've actually been able to pull all of those models straight into Claude with the AI box MCP. It's amazing. I've created tons of Facebook ads this week. And the thing that actually saved me a ton of money and also just time is I was creating a bunch of podcast covers for a project where it was a it was a language learning podcast. So it's like learn German, right? And it'll be a podcast in German. But my problem was I was like, you know, people that are from, you know, Spain or from Russia that want to learn German, they're not going to search for learn German in English or even learn German in however you say it in in Dutch, they're going to search it in their own language of Russian or whatever. So anyways, I have this problem. And the solution is generating podcast covers with ChatGPT. You know, learn, you say the words learn German, and you translate it to 10 different 10 different languages. Okay, so I had this great podcast cover design that I really like. And I was just getting ChatGPT, I was giving it to it, it was spitting out a new title. And I know a lot of people are like, Oh, why don't you just use Canva to do this? Yeah, you could use Canva to do it. And then you'd have to manually adjust like the font sizes. Because once you get into like Mandarin or Korean, and like the languages are completely different. I had two different fonts and two different colors. And anyway, I was gonna have to go Finnick with it. And it was going to be annoying. So I was having chat GPT just one shot this, but it was taking forever. And then this for this particular project, I'm actually doing every language and every language is variant, right? So it'd be like learn English, learn German, learn French, their podcasts in those languages. But it's I'm making a podcast cover for every language, right? So there'd be like 10 or 12 variations of everything. Anyways, it was a big project, it was going to take forever to generate 300 podcast covers for every language variant. And so what I did is I had Claude make, you know, the base image for every single one of these, which is like 12 languages. So it just made the base image for the 12 languages. And then Claude actually put the text on it, it can swap out. It saved me so much time being able to use Claude plus AI box. If I was just going to chat GPT and trying to get, you know, 300 images generated, this would take me forever. But getting Claude to basically, I had the AI box MCP called in. So it just said, Hey, you know, Claude knew exactly what to do. It wrote the prompt, I give it an image and told it what I wanted it to do. ([Time 0:00:57](https://share.snipd.com/snip/d1757494-c158-4dd0-95c4-ac38e624dfad)) - **Opus 5 Delivers Near Fable Power At Half Cost** - Claude Opus 5 matches Fable 5 performance closely while costing roughly half per call, making it a practical substitute for many tasks. - Jaeden plans to switch from Fable 5 to Opus 5 for routine work to cut token spend significantly. Transcript: Jaeden Schafer I was doing last night with it I tested it out go try out the AI box MCP if you haven't already it can generate images audio video right inside of Claude You use Claude's brain and by the way, It's not just Claude like you can do the same thing inside of codex or inside of cursor or inside of Any of these other tools that pull MCPs in okay, let's talk about what's going on with Opus 5 this one's actually a pretty fun model because the biggest issue that i've seen with claude at this point is that fable 5 which i use i burn through credit super fast but it also burns Through all of my tokens for my entire account so the new opus 5 is very similar on the benchmarks it's slightly worse than fable 5 but very close And it is half the cost. This is amazing. I will take a, you know, a 10% or a 5% cut on, you know, brainpower, quote unquote, in order to get half the cost down because I'm just burning through so many tokens using it. I only use it for like the most important critical tasks. So I think from now on, I probably just won't use Fable 5. I'll just be using Opus 5 for everything. ([Time 0:04:05](https://share.snipd.com/snip/71f84b41-4b98-4b5c-8f02-e3a3a1f962f5)) - **ChatGPT Voice Turns The Desktop Into A Voice Agent** - OpenAI added ChatGPT Voice to the desktop app so voice interactions can control apps and files, not just chat. - The feature uses app-shots to let agents see screen contents and alt-text, enabling debugging, file actions, and programmatic fixes while you talk. Transcript: Jaeden Schafer But in the meantime, I'm still using Claude till that runs out. But anyways, I think Claude knows this. And so they're making basically trying to get themselves on par with OpenAI, come up with all the features that were just launched. And speaking of really cool features from OpenAI, OpenAI actually just added chat GPT voice to the desktop app. If you remember, I don't know if you, you know, everyone's at a different phase. But basically, OpenAI has a desktop app called chat GPT. They used to have one called Atlas, which was like a browser. And they had one called Codex, which was for coding, they combined them all. It's just called the ChatGPT app. And they now have ChatGPT voice that they've added to it, which what that means is it lets you talk to ChatGPT, to this thing that controls your computer, right? It does everything that Claude Cowork can do where it like controls your computer, can control your files, it can open your browser, can control your browser, it can do all that kind Of stuff. But while you're talking to it, so you can have something pulled up on your computer screen. And you can be writing code instead of like, I do this all the time with Claude, I go take a screenshot of whatever I'm working on. And then I, you know, drop it into Claude. And I'm like, what do you think about blah, blah, blah. Okay, now with Chai Chippity voice, you can have something pulled up on your computer screen, and you could just be talking to it. You're like, hey, you know, I'm on my emails and it looks like they said this thing is missing or I'm in my files or I'm in my software and there's this issue. And it's looking at it and it can then debug it and test it right from there. ([Time 0:05:35](https://share.snipd.com/snip/8fdec436-8578-427a-bd48-e56e7633d072)) - **Claude Found An Undocumented API To Export 300 Hours** - Jaeden had Claude inspect his Riverside podcast account and discovered an API and download keys, letting the model automate bulk exports that the platform refused to provide. - Claude executed programmatic steps rather than only visually clicking UI elements. Transcript: Jaeden Schafer So like I have a project where I have to download 300 hours of podcast video content from the platform that I hosted all on Riverside. I've been recording there for years. I wanted to export all my podcasts off of there. And I, you know, I like email their support. And I'm like, Hey, do you guys have a bulk like export thing, whatever, I'll pay extra. They're like, Nope, sorry, there's nothing we can do no bulk export, you got to go manually click every single one. And you only can do 15 hours a month. And I'm like, I have 300 hours. What do you mean? Anyways, so there's like a couple little loopholes they came up with, it was super annoying. Obviously, I'm not going to spend a week of my life manually, like exporting every single thing. So I got Claude to go look at it. And when Claude went in there, it was like, hey, look, we actually found an API inside of this and we're able to like automate and manual or, you know, automate a lot of the stuff and download Everything we found like the download keys and the files and whatever. So Claude's in there doing who knows what, but it's not just like looking at my computer screen and clicking on actual buttons. It's like executing code to go and do a lot of this stuff programmatically, which is really cool. And I mean, basically that's what this new Mac OS feature is able to do beyond just looking at what's on your screen. It looks at what the code is of the alt text, the code what's behind the actual screen. ([Time 0:07:27](https://share.snipd.com/snip/a83fa4e6-0669-4f05-a441-f3c937fdfcce)) - **Meta Moves Its AI From Viral Gimmicks To Productivity** - Meta is shifting its AI from novelty chat experiences toward productivity features like calendar access, daily briefings, and recurring task automations. - Jaeden notes Meta's distribution (WhatsApp, Instagram, Messenger) could drive fast adoption if they execute. Transcript: Jaeden Schafer Meta is pivoting their AI chatbot from just being kind of like entertainment. They're trying to focus more productivity. In the past, you've probably seen all the branding with Meta where it was like, chat with the Mr. Beast AI on WhatsApp and like, go generate an image of your friends generate a picture of you as a pirate, right? Like this is kind of like the fun viral stuff that they were working on. But I think at the end of the day, they're realizing people are not going to pay for that. Like it's fun. And it's a novelty. And maybe it was cool, like, I mean, years ago, but it's just not really driving actual usage today. And so they're now moving more towards productivity, more in line with what Claude and what ChatGPT are doing. They're adding calendar access, they're adding daily briefings, they're adding recurring task automations that directly compete with, like I have task automations on Claude that Will run every week or every day or some of them every three hours, depending on what the task is. So I think we're seeing a big shift for meta, they're getting away from just being fun, and they're going to productivity. And I think we're going to see them get a big spike in in usage. Meta can also now read your calendar, it can plan events, it can look at Facebook marketplace for items within a certain budget, which is kind of funny, because I remember chat GPT was Doing this for a lot of people with chat GPT agents, they're like getting into lowball people in marketplace. But anyways, I guess you can now do that with MetaZone agent. ([Time 0:09:14](https://share.snipd.com/snip/c55c5a58-d605-4701-b510-05f79d13b6e8)) - **Silicon Valley Pushes Back Against Open-Weight Restrictions** - Over 200 companies including Hugging Face and Meta signed a letter urging the White House not to restrict open-weight AI or model distillation. - Jaeden highlights the irony of large labs opposing distillation after they trained on the open internet themselves. Transcript: Jaeden Schafer Hugging Face, Meta, and Microsoft, Mistral, and NVIDIA are all signing an open letter. And I think there was like 200 other companies that did, the White House not to restrict open way AI models or ban the technique of training one model on another model's outputs model Distillation. This is so fascinating, because there's a, you know, this letter in particular, they're pushing back on a plan to respond to Chinese AI labs by penalizing open source development alongside IP theft. Now, this is coming from I was reading the tweet earlier today from Secretary Bessett from the Treasury. And he basically came up with this tweet, which I mean, I don't know anything about the government, but I don't know why our Treasury Secretary is weighing in on open source AI models, But whatever. And basically, he was saying, Hey, look, the Chinese labs are doing model distillation asking, you know, Claude to give them like 5000 answers to a question. And they use those 5000 answers to help train their model. Now, a lot of open source models are using this using the same tactic. Some people think it's unethical. In my opinion, I just think it's so ironic, because anthropic just spent $20 million, they paid another $20 million to a group that is kind of fighting against this anthropic is constantly Saying, hey, look, we're being like model distilled by Chinese labs. And they come up with these big reports. And like, yeah, I don't want to just spend all of our money and then give the give the secret sauce to the Chinese models for free. ([Time 0:10:56](https://share.snipd.com/snip/862c527e-7448-4ab2-b1de-0c20c3e746fe)) - **AlphaFold Redesigns Cas9 To Cut Off-Target Edits** - Researchers used AlphaFold to redesign Cas9, reducing harmful off-target edits from 28% to 5% while preserving on-target accuracy. - A Chinese team tested 23 amino acid swaps at 10 positions and found major specificity improvements despite similar protein shape. Transcript: Jaeden Schafer Researchers have just used AlphaFold to redesign CRISPR-Cas9 to cut harmful off-target edits from 28% down to 5% while keeping the gene editor's accuracy on intended targets intact. So this is kind of a science one for you, but I'm excited about this because basically off-target cuts are things that will damage healthy genes in patients. So they want to do some of this CRISPR gene editing stuff. But if you have these offcuts, it's really bad for you. So they use alpha fold to cut that down, which is really cool. It's basically a big step in safer gene therapies, which I'm excited about. There was a Chinese team that tested 23 amino acid swaps at 10 key positions, and they published the results in nature today about this and they found that over 95% of the off target sites Changed which amino acids inside of Cas9 touched the guide RNA even when the proteins overall shape stayed the same. So you know, they've made some massive improvements there. ([Time 0:15:19](https://share.snipd.com/snip/0d346792-6e4c-498f-b3c6-29a5e1c8aecd)) - **MidJourney Buys Co–Star To Build A Real App Team** - MidJourney acquired Co–Star, a social astrology app with 4.3 million monthly users, to onboard 24 consumer app builders and accelerate building a standalone MidJourney app. - Jaeden suspects the acquisition is talent- and distribution-driven rather than product alignment. Transcript: Jaeden Schafer Mid journey, this is a company that's been generating images for a long time, but it's kind of stuck inside of Discord. And I guess they do have their own website. You can access them. I'm going to be honest. I have not used Midjourney. They might be the best image model in the world. I'm not sure. Last thing I remembered is they signed a deal with Meta to get embedded to power their image models. But it's really hard to use them because they're just inside of Discord and on their own website. They don't have like an app. So anyways, there's just less surfaces for them to touch. I think they've been struggling because of that. And their response to this is that they've actually went and acquired a company. It's called CoStar. It is a social astrology app with 43 million monthly users. It has nothing to do with MidJourney. But what's interesting about this is that it's pulling in 24 consumer app builders into mid journey. So in my opinion, the reason why they're buying this, they're like, Look, we need to build an app, let's go buy a successful app, and bring all their developers in and they can help build The mid journey app for us. And you know, they won't be just a discord only tool. CoStar that as it currently sits, it just generates horoscopes using AI, and they say also human writers. I'm sure AI does a ton of this stuff. Then it lets users share astrology charts with their friends. There's like some social features and horoscope stuff that's in there. But regardless, Midjourney basically has no iOS or Android app and, you know, OpenAI, Google, Anthropoc, like everyone has one, every major tool. And so I think mid journey right now is building is yeah, basically trying to build the team that does this. It's also interesting, because mid journey feels like a little bit all over the place, maybe not super, but they also have like a medical division where they're building like physical Spa concepts that scan your whole body and tell you if you have any issues. So they're working on a couple different things. But I would say this astrology app isn't just like a new pivot or direction for them. I'm pretty sure this astrology app is they're grabbing 24 talented people. And they're going to build out impressive mid journey app, which I'm excited for. And by the way, mid journey would be an incredible company if they just built an API, AI box, my company where I you know, I have over 80 different AI models inside of there, we don't have AI or we don't have MidJourney on there, which is a huge bummer, but it's just because they don't have an API. ([Time 0:16:22](https://share.snipd.com/snip/ce4d94c7-99e4-4da8-8ced-9a1a5fbd346c)) - **Plug Many Models Into Claude With AIbox MCP** - If you want multimodal access inside Claude, use AIbox.ai's MCP to plug 80+ models into Claude and other agents instead of subscribing to many single-model services. - Jaeden says the $8.99 plan centralizes image, audio, and video generation into Claude workflows. Transcript: Jaeden Schafer And people have made like unofficial APIs that go and like make an account and they're like kind of scraping Discord, but like unofficial APIs could get your account banned. It could crash anytime some UI thing or something changes with MidJourney, they'll stop working. It's just not reliable. We can't use it as probably against their terms. So anyways, if they made an API, we'd include them and they would get access to, you know, thousands more users from us. And eventually millions more users from the overall development community. So I think that would probably be the biggest thing they could do. We'll see what happens with a mid journey API. Guys, thank you so much for tuning into the podcast. If you want to get images, audio, video inside of Claude inside of whatever AI tools you using, 80 different ones, instead of paying $20 subscriptions to every platform, go and get an $8.99 subscription to AIbox.ai. You get every single AI model and it plugs into Claude and everything else with an MCP. So talk to Claude, an image pops up inside of there. You can literally see the image. You can edit it in there. I use it all the time for making websites where I'll, you know, every website looks like AI slop and I'll be like, Hey, go use AI box to generate custom graphics for this website. And it makes it look beautiful. ([Time 0:18:27](https://share.snipd.com/snip/9c46d66d-1d98-499d-9237-96fb6d4cae55))