Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

I’ve been using GPT-5.6 Sol internally for the past two months, I've spent probably 25+ billion tokens. Here’s my review and comparison to Fable 5: > Let's start with the analogy because everyone seems to be giving theirs - GPT-5.6 is likely the last version of the GPT-5 training... run series. It's kind of like an athlete at their peak. Through years of experience in the game, they've become the most reliable player and has the highest game IQ. But, there's no more room to grow. Fable on the other hand, being essentially the first version of a new training run, is the first round draft pick rookie. Raw talent mixed with the energy only a young person would have results in some incredible plays we didn't think possible, but also mistakes due to lack of experience. But that rookie will only improve and likely will be better than the veteran ever was because it's a new game and a new era. > GPT-5.6 is genuinely better at long, sustained work. With /goal, I've had it running complex projects for days with almost no intervention. It built a Minecraft-style game, kept adding features and mobs after the core game worked, and only stopped because I stopped the run. I never felt as though I had to jump in and guide it back to the right path. > It keeps finding useful work when you give it a concrete finish line. I had it recreate Excel with a loop. It inspected the real desktop excel app with Computer Use, comparing that against its own build, and closing the gaps. I stopped it after six days after it had built an incredible amount of functionality. > It's faster than other models in two different ways. The raw generation speed is higher, something OpenAI has been putting effort into. But it also takes a shorter path to solutions. It wanders less, changes less code, and generally knows how to get things done directly. In daily use, it feels about 2-3x times faster than Fable. That's my impression, not a controlled benchmark. The difference is large enough that I notice it constantly. > It works well across a wide range of tasks. I use it for one-line edits, quick questions, browser chores, and multi-day builds without changing my prompting style. Speaking of browser control, its the best ever I've used. To the point where I actually use it often. If a task lives on a website, GPT-5.6 usually opens the browser and does it there instead of asking for an API key or forcing everything through the terminal. When I switched back to GPT-5.5, it went straight to the command line even when the browser was clearly the better tool. > And it can handle real browser work, not just toy demos. During a data import, I had it monitor Supabase and resize instances as the load changed. It stayed on the dashboard, adjusted capacity, and checked the result without an API or a custom script. > I also gave it a full Google Workspace migration. It moved Forward Future from to preserved the old aliases, and configured MX, SPF, and DKIM. Before a consequential save, it stopped, explained exactly what would change, and waited for confirmation. > The reasoning setting matters a lot. Light is good for questions and small edits. High and Extra High are the sweet spots for serious work. Ultra usually takes longer than the extra thinking is worth and burns tokens. > I love that 5.6 is split into 3 sizes. Not only can you control speed and cost that way, but you still also have the thinking effort setting for each of them. Very precise controls. I just wish Codex automatically routed my prompts for me. > Its personality is blunt and a little bland. Claude feels warmer and more natural to talk to. GPT-5.6 is more clinical, but I like that for work. It gives me enough explanation and rarely pads the answer. I usually have to ask Fable to explain things more simply and/or more concise. > Its front-end taste has improved, but the default is predictable. Left alone, it turns websites into PowerPoint decks with huge statements and hard section breaks. The good news is that it takes design direction well and can revise without destroying the parts that already work. > It still makes confident mistakes. I asked it to rebuild parts of a system, and it told me the job was finished. Later, I found out it wasn't. Bits of its internal process also leak into the answer occasionally. > Claude Fable is more naturally autonomous on large, open-ended projects. GPT-5.6 is easier to reach for. I don't need to invent a huge project to justify using it. It works just as well for a small edit or browser chore. > GPT-5.6 is also cheaper. Sol costs $5 per million input tokens and $30 per million output tokens. Fable costs $10 and $50. Cached input is cheaper too. Still, cost per finished task matters more than cost per token. > GPT-5.6 isn't the best at everything, and it still needs supervision. But it generates faster, wanders less, works at almost any scale, and wastes less of my time. It's the model I have the most confidence in to get the job done right the first time. I put together a full breakdown with all the tests, prompts, and examples on a site. You can read it here:show more

Matthew Berman

126,876 subscribers

179,362 görüntüleme • 2 gün önce •via X (Twitter)

Bilim & Teknoloji Oyun Eğitim

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

228,126 görüntüleme • 22 gün önce

BREAKING: GPT-5.6 Sol is out—AND Codex has been merged into ChatGPT Desktop as ChatGPT Codex. This combo model and desktop app harness are the gold-standard for knowledge work in AI. 5.6 is powerful, fast, half the price of Fable, and my default for almost everything. We’ve been testing it internally Every 📧 for about a month across coding, writing, design, and knowledge work. Here’s our day-zero vibe check: - An A-tier coder—but it’s not Fable. Sol scored 56/100 on our Senior Engineer benchmark compared to a 91 for Fable. I think the 56/100 undersells it, it's an excellent implementor, and very smart. But Fable just writes conceptually cleaner code and works better at the top end of task complexity. PRO-TIP: Use GPT-5.6 as Fable's subagent for the most goated combo in AI coding. - The best writer of the frontier models. It’s clearer and more concise than Fable or Opus 4.8, without the overexplaining or weird private language. It can one-shot marketing emails, help you workshop taglines, and explain complex concepts clearly. It's also super fast, which makes it easy to collaborate with. - Design is better, but not top-tier. It has noticeably more taste than 5.5, but Fable and Opus 4.8 are still playing at a different level. See examples in the video and vibe check below. - The real leap is knowledge work. Sol is the first model I’ve trusted to run whole loops of knowledge work—not just help with individual tasks. I use it to process email, surface decisions from meetings and Slack, find job candidates, scan Facebook Marketplace for furniture, and log my meals. It has shifted my job from doing the work to tending the system that does it. - The merged app is fine. I was extremely worried about this because I love the Codex app. OpenAI was caught in an interesting position: How to make an agent orchestration app for regular ChatGPT consumers, coders, and businesses all in one app. They now split the interface between ChatGPT Work and ChatGPT Codex. They're basically the same except Work hides code. And "Chat" has been demoted to 2nd tier status for quick questions in either one. It's not a big leap, but it's not a huge setback either. And it remains my favorite of the desktop agent orchestration apps. Verdict: If I really had to put my finger on it, I'd say Fable has way more big model smell. But that means it's a skill in itself to get value out of it—99% of people are still not there yet. GPT-5.6 is almost as powerful, but is easy to use, fast, and relatively cheap. It should give you an early sense of where model work is going. Full Every 📧 Vibe Check:

BREAKING: GPT-5.6 Sol is out—AND Codex has been merged into ChatGPT Desktop as ChatGPT Codex. This combo model and desktop app harness are the gold-standard for knowledge work in AI. 5.6 is powerful, fast, half the price of Fable, and my default for almost everything. We’ve been testing it internally Every 📧 for about a month across coding, writing, design, and knowledge work. Here’s our day-zero vibe check: - An A-tier coder—but it’s not Fable. Sol scored 56/100 on our Senior Engineer benchmark compared to a 91 for Fable. I think the 56/100 undersells it, it's an excellent implementor, and very smart. But Fable just writes conceptually cleaner code and works better at the top end of task complexity. PRO-TIP: Use GPT-5.6 as Fable's subagent for the most goated combo in AI coding. - The best writer of the frontier models. It’s clearer and more concise than Fable or Opus 4.8, without the overexplaining or weird private language. It can one-shot marketing emails, help you workshop taglines, and explain complex concepts clearly. It's also super fast, which makes it easy to collaborate with. - Design is better, but not top-tier. It has noticeably more taste than 5.5, but Fable and Opus 4.8 are still playing at a different level. See examples in the video and vibe check below. - The real leap is knowledge work. Sol is the first model I’ve trusted to run whole loops of knowledge work—not just help with individual tasks. I use it to process email, surface decisions from meetings and Slack, find job candidates, scan Facebook Marketplace for furniture, and log my meals. It has shifted my job from doing the work to tending the system that does it. - The merged app is fine. I was extremely worried about this because I love the Codex app. OpenAI was caught in an interesting position: How to make an agent orchestration app for regular ChatGPT consumers, coders, and businesses all in one app. They now split the interface between ChatGPT Work and ChatGPT Codex. They're basically the same except Work hides code. And "Chat" has been demoted to 2nd tier status for quick questions in either one. It's not a big leap, but it's not a huge setback either. And it remains my favorite of the desktop agent orchestration apps. Verdict: If I really had to put my finger on it, I'd say Fable has way more big model smell. But that means it's a skill in itself to get value out of it—99% of people are still not there yet. GPT-5.6 is almost as powerful, but is easy to use, fast, and relatively cheap. It should give you an early sense of where model work is going. Full Every 📧 Vibe Check:

Dan Shipper 📧

140,781 görüntüleme • 2 gün önce

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 görüntüleme • 11 ay önce

Pragmata Review | No spoilers That is it for me. I played more than 30 hours of Pragmata and I am really happy that not only we finally got this game after so many delays and in a time where cancellations are common, but also that it turned out to be a very solid and enjoyable experience. Visually it is beautiful, and gameplay wise it works well for the length it has. It is not a long game, which I personally prefer, and I hope we see more titles like this instead of games trying to be longer just for the sake of it. I would not call it short like some people did, but I think it is exactly as long as it needs to be. Story wise, it is my favorite of the year so far. Seeing this kind of father and daughter dynamic again made me want to play more games with similar themes. I did almost everything in the game and I absolutely recommend it. If you are unsure about the length, maybe wait for a sale, but quality wise it deserves to be up there. I am not someone who rushes, so it took me longer because I admire the environments, take screenshots, record videos, and try to find collectibles without guides. For someone who just plays straight through, I think it would take around 12 to 15 hours, maybe a bit more or less. This is the kind of experience I want to see more often in the gaming space. I liked the combat and I think the enemy variety is fine for the length. If the game was longer without adding new enemy types, it would probably feel repetitive, but for what it is, it works. My biggest concern before playing was the combination of Hugh’s shooting and Diana’s hacking. If it was too complicated, it would be annoying, and if it was too simple, it would be boring. Thankfully, it ended up being exactly right. My only real complaint is that you need to return to the base to restock items, and when you die, the game sends you back there instead of placing you right before the area or at the last travel point you unlocked. It is not a huge issue, but it breaks the flow a bit. Diana is very cute and does her part extremely well, and Hugh is a character that is hard not to like. They both nail the dad simulator vibe. The voice acting is great, especially for Diana. Capcom delivered a unique and impressive new IP, which is always welcome in an industry where big publishers mostly rely on established franchises instead of taking risks. Whether we get more entries in the future is up to them, but it is also up to us to support games like this if we want more of them. On PC the game runs very well. The only thing that felt a bit underwhelming to me is the ray tracing when you use it on its own without path tracing. In some areas it does not add much, similar to what I noticed in Resident Evil Requiem. It makes me think it is either something with the RE Engine or simply that Capcom does not push ray tracing that far and focuses more on path tracing instead. Path tracing looks incredible, but of course it comes with a heavy performance cost. Something that impressed me throughout the entire playthrough is how consistent the game feels from start to finish. There is no point where it suddenly drops in quality or feels rushed. Every area has its own atmosphere, the pacing stays steady, and the game never tries to drag itself out longer than needed. It is rare to play something that stays this steady all the way through, and that alone made the whole experience even more enjoyable for me. I hope we get a DLC or a sequel one day, but even if this stays a one off, I am happy with what we got. Rating: 9/10

Pragmata Review | No spoilers That is it for me. I played more than 30 hours of Pragmata and I am really happy that not only we finally got this game after so many delays and in a time where cancellations are common, but also that it turned out to be a very solid and enjoyable experience. Visually it is beautiful, and gameplay wise it works well for the length it has. It is not a long game, which I personally prefer, and I hope we see more titles like this instead of games trying to be longer just for the sake of it. I would not call it short like some people did, but I think it is exactly as long as it needs to be. Story wise, it is my favorite of the year so far. Seeing this kind of father and daughter dynamic again made me want to play more games with similar themes. I did almost everything in the game and I absolutely recommend it. If you are unsure about the length, maybe wait for a sale, but quality wise it deserves to be up there. I am not someone who rushes, so it took me longer because I admire the environments, take screenshots, record videos, and try to find collectibles without guides. For someone who just plays straight through, I think it would take around 12 to 15 hours, maybe a bit more or less. This is the kind of experience I want to see more often in the gaming space. I liked the combat and I think the enemy variety is fine for the length. If the game was longer without adding new enemy types, it would probably feel repetitive, but for what it is, it works. My biggest concern before playing was the combination of Hugh’s shooting and Diana’s hacking. If it was too complicated, it would be annoying, and if it was too simple, it would be boring. Thankfully, it ended up being exactly right. My only real complaint is that you need to return to the base to restock items, and when you die, the game sends you back there instead of placing you right before the area or at the last travel point you unlocked. It is not a huge issue, but it breaks the flow a bit. Diana is very cute and does her part extremely well, and Hugh is a character that is hard not to like. They both nail the dad simulator vibe. The voice acting is great, especially for Diana. Capcom delivered a unique and impressive new IP, which is always welcome in an industry where big publishers mostly rely on established franchises instead of taking risks. Whether we get more entries in the future is up to them, but it is also up to us to support games like this if we want more of them. On PC the game runs very well. The only thing that felt a bit underwhelming to me is the ray tracing when you use it on its own without path tracing. In some areas it does not add much, similar to what I noticed in Resident Evil Requiem. It makes me think it is either something with the RE Engine or simply that Capcom does not push ray tracing that far and focuses more on path tracing instead. Path tracing looks incredible, but of course it comes with a heavy performance cost. Something that impressed me throughout the entire playthrough is how consistent the game feels from start to finish. There is no point where it suddenly drops in quality or feels rushed. Every area has its own atmosphere, the pacing stays steady, and the game never tries to drag itself out longer than needed. It is rare to play something that stays this steady all the way through, and that alone made the whole experience even more enjoyable for me. I hope we get a DLC or a sequel one day, but even if this stays a one off, I am happy with what we got. Rating: 9/10

𝑨𝒔𝒉𝒆𝒏 𝑶𝒏𝒆

32,822 görüntüleme • 2 ay önce

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper 📧 for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper 📧 for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch

GREG ISENBERG

142,297 görüntüleme • 2 gün önce

"At school or university, the thing is to be brilliant and to get the answer right first time. And there are brilliant people who can do that, but for the rest of us, we're not brilliant. And to get there, we have to strive and we have to go through failure. And we realize that you don't get it right first time, you don't get it right second time. In my case, and I counted it, it's 5,127 times. One of the things I always want to say is that sounds like a struggle. It was a struggle, but actually it was a hugely enjoyable struggle. The debt was mounting and I had three children, a wife and a home, and then a mortgage to pay, like everybody else. But I had a real point in life, I had a real aim and I had to get there. And the failures were interesting because I'd learned from every single one of them."

"At school or university, the thing is to be brilliant and to get the answer right first time. And there are brilliant people who can do that, but for the rest of us, we're not brilliant. And to get there, we have to strive and we have to go through failure. And we realize that you don't get it right first time, you don't get it right second time. In my case, and I counted it, it's 5,127 times. One of the things I always want to say is that sounds like a struggle. It was a struggle, but actually it was a hugely enjoyable struggle. The debt was mounting and I had three children, a wife and a home, and then a mortgage to pay, like everybody else. But I had a real point in life, I had a real aim and I had to get there. And the failures were interesting because I'd learned from every single one of them."

David Senra

137,486 görüntüleme • 7 ay önce

Cameron Young is playing with a golf ball that would allegedly be compliant with the new roll back rules that will come into effect in a few years time. He was asked about it ahead of the PGA Championship and he says every player in the game is sacrificing distance for control, and he put it in play at the Wyndham last year which he won. “I think I put it in play the same reason that everybody else plays the ball that they play. I hit it during a ball test, one of the Titleist facilities probably close to two years ago and didn't know anything about it and just kind of say, hey, what's that one? Because I liked the flight. “Then as things progressed, I was able to test it last year at Wyndham, able to put that in play, and it's been there since. “Obviously there is no conforming list. I wasn't aware that it would have -- I suppose I read something that said it passed that test, but I wasn't aware of that until very recently. “So at no point was that a consideration. It was just really me trying to optimize my golf, and it's the ball that seems to work the best for me.” He then was asked whether he lost distance with it compared to other balls he’s tested: “Not particularly. I don't think any of us are out really here playing the ball that goes the farthest. I think you'd struggle to find a single person that's doing that. We're all sacrificing a certain amount of things that we feel are worth it, control with irons, control with wedges. For me, that's the biggest thing is being able to control spin, and this is the ball that does the best for me.” Finally he can as asked whether this ball goes further than the one he was using: “No, I hit very similar, yeah. It's much more -- the driver is kind of the easiest thing to deal with, I feel like. For me to get it where it needed to be, I had to just add a little bit of spin, and it kind of comes out at a perfectly playable range. “For me, the biggest thing, like I said, is the irons. This ball is easier to control with the irons. It doesn't spin as much, and it just allows me to be better with my distance control just because it's more consistent.” The golf ball rollback has been a hugely controversial subject but Cameron Young is currently using one that’s compliant and he is playing the best golf of his career. This gives the best idea yet on what impact, or lack of it, the new rules will actually have on the sport. PGA Championship

Cameron Young is playing with a golf ball that would allegedly be compliant with the new roll back rules that will come into effect in a few years time. He was asked about it ahead of the PGA Championship and he says every player in the game is sacrificing distance for control, and he put it in play at the Wyndham last year which he won. “I think I put it in play the same reason that everybody else plays the ball that they play. I hit it during a ball test, one of the Titleist facilities probably close to two years ago and didn't know anything about it and just kind of say, hey, what's that one? Because I liked the flight. “Then as things progressed, I was able to test it last year at Wyndham, able to put that in play, and it's been there since. “Obviously there is no conforming list. I wasn't aware that it would have -- I suppose I read something that said it passed that test, but I wasn't aware of that until very recently. “So at no point was that a consideration. It was just really me trying to optimize my golf, and it's the ball that seems to work the best for me.” He then was asked whether he lost distance with it compared to other balls he’s tested: “Not particularly. I don't think any of us are out really here playing the ball that goes the farthest. I think you'd struggle to find a single person that's doing that. We're all sacrificing a certain amount of things that we feel are worth it, control with irons, control with wedges. For me, that's the biggest thing is being able to control spin, and this is the ball that does the best for me.” Finally he can as asked whether this ball goes further than the one he was using: “No, I hit very similar, yeah. It's much more -- the driver is kind of the easiest thing to deal with, I feel like. For me to get it where it needed to be, I had to just add a little bit of spin, and it kind of comes out at a perfectly playable range. “For me, the biggest thing, like I said, is the irons. This ball is easier to control with the irons. It doesn't spin as much, and it just allows me to be better with my distance control just because it's more consistent.” The golf ball rollback has been a hugely controversial subject but Cameron Young is currently using one that’s compliant and he is playing the best golf of his career. This gives the best idea yet on what impact, or lack of it, the new rules will actually have on the sport. PGA Championship

Flushing It

311,493 görüntüleme • 1 ay önce

The truth about 5.6 sol after using it all day : The hype is overblown. Sort of. The benchmarks, and the commentary on X convinced me we were receiving AGI that runs at hyper speed, and is insanely cheap. in reality, 5.6 is built on the same spud pretraining as 5.5 this means its a nice bump, but not the opus to fable 5 LEAP in intelligence we recently experienced from anthropic. 5.6 is 2x times cheaper than fable on paper, and actually 3x cheaper when you look at actual task execution because of its token efficiency. BUT on swe bench where the models have to fix actual github bugs it falls behind fable pretty big. For vibecoders like myself this means I will be using 5.6 sol as a worker agent for Fable 5 to orchestrate alongside grok 4.5 I love this new era.

The truth about 5.6 sol after using it all day : The hype is overblown. Sort of. The benchmarks, and the commentary on X convinced me we were receiving AGI that runs at hyper speed, and is insanely cheap. in reality, 5.6 is built on the same spud pretraining as 5.5 this means its a nice bump, but not the opus to fable 5 LEAP in intelligence we recently experienced from anthropic. 5.6 is 2x times cheaper than fable on paper, and actually 3x cheaper when you look at actual task execution because of its token efficiency. BUT on swe bench where the models have to fix actual github bugs it falls behind fable pretty big. For vibecoders like myself this means I will be using 5.6 sol as a worker agent for Fable 5 to orchestrate alongside grok 4.5 I love this new era.

Max Blade

34,887 görüntüleme • 1 gün önce

I got to try Grok 4.5 in early access in Cursor for the past few days and I absolutely enjoyed it. It feels like Opus 4.8 at 2x the speed at a much cheaper price point. I tasked it to brainstorm > plan > implement a big feature for my game (this act 1 boss fight) and it did not disappoint. - It is much smarter than Composer 2.5, during planning mode, it is able to think through my request more robustly, ensuring that edge cases are covered and makes sure to ask the right questions to confirm with me first. - It is much better at brainstorming ideas/suggestions, similar to Opus 4.8, though I think Fable still edges out a little when it comes to brainstorming ideas and suggestions - It is FAST. probably the fastest of all frontier models (Opus 4.8, GPT 5.5 etc), which makes it a joy to build with, because I can stay in the flow - It has much improved visual/animation capabilities than Composer 2.5, it can code up animations (i wanted an explosion animation with particle effects) with much, much better visuals, animation movement and timing. This is a big leap and I was so happy to see this improvement. - The best part for me is that I can just use the same model from planning down to execution without switching to a lower cost model because the price point is cheaper than other frontier models. I'll be testing this model with more challenging tasks in the next few days but I think this is going to be my main driver for vibe coding for a while. Also, its nice to see Grok back in the race. 🙌

I got to try Grok 4.5 in early access in Cursor for the past few days and I absolutely enjoyed it. It feels like Opus 4.8 at 2x the speed at a much cheaper price point. I tasked it to brainstorm > plan > implement a big feature for my game (this act 1 boss fight) and it did not disappoint. - It is much smarter than Composer 2.5, during planning mode, it is able to think through my request more robustly, ensuring that edge cases are covered and makes sure to ask the right questions to confirm with me first. - It is much better at brainstorming ideas/suggestions, similar to Opus 4.8, though I think Fable still edges out a little when it comes to brainstorming ideas and suggestions - It is FAST. probably the fastest of all frontier models (Opus 4.8, GPT 5.5 etc), which makes it a joy to build with, because I can stay in the flow - It has much improved visual/animation capabilities than Composer 2.5, it can code up animations (i wanted an explosion animation with particle effects) with much, much better visuals, animation movement and timing. This is a big leap and I was so happy to see this improvement. - The best part for me is that I can just use the same model from planning down to execution without switching to a lower cost model because the price point is cheaper than other frontier models. I'll be testing this model with more challenging tasks in the next few days but I think this is going to be my main driver for vibe coding for a while. Also, its nice to see Grok back in the race. 🙌

Danny Limanseta

1,311,553 görüntüleme • 3 gün önce

We have now fully commissioned the machine after a few hiccups related to an old dying hard drive in the machine PC (it had a 1 gb hard drive!!) could save the machine in the nick of time with the help of a fellow machining junkie who knew how to do it! But the real reason i am writing is that we successfully ran our first 3D program on it and that the program was written entirely using Claude !! I did it myself and it took me a few hours to get it going. The best part of using Claude was that I could ask it to use macros to write the program which meant i could control *all* variables in the program. And it ran like a charm! Rendered on the part a fine finish and a brilliant high to see the part come out better than expected! I set the job myself because I wanted to get a feel for the machine, its ways and how to work with it. It had been nearly 15 years since I had set a job on the machine for a VMC, and it felt good to know the craft has not left my hands and getting them dirty while making parts still makes me happy! Samaachar samaapth :)

We have now fully commissioned the machine after a few hiccups related to an old dying hard drive in the machine PC (it had a 1 gb hard drive!!) could save the machine in the nick of time with the help of a fellow machining junkie who knew how to do it! But the real reason i am writing is that we successfully ran our first 3D program on it and that the program was written entirely using Claude !! I did it myself and it took me a few hours to get it going. The best part of using Claude was that I could ask it to use macros to write the program which meant i could control all variables in the program. And it ran like a charm! Rendered on the part a fine finish and a brilliant high to see the part come out better than expected! I set the job myself because I wanted to get a feel for the machine, its ways and how to work with it. It had been nearly 15 years since I had set a job on the machine for a VMC, and it felt good to know the craft has not left my hands and getting them dirty while making parts still makes me happy! Samaachar samaapth :)

Sanjeev

11,761 görüntüleme • 4 ay önce

Jon Rahm on the LIV format: “Yeah, obviously there’s been a bit of a change. There was a lot more about LIV Golf that was attractive to me, right. Yeah, maybe the format was a set back in the past, but at the same time there’s a lot of positives to it as well. And one of the things that a lot of players kept mentioning is you don’t have a wave weather difference, where you can simply get unlucky and you’re out of contention for that tournament. It’s part of the game, I get it, but it’s something you don’t have to deal with anymore. So that part is a very nice aspect. The team is what really made it for me. Being able to be part of a team, represent a team, play for my teammates, with my teammates and against my teammates, is something that to me that has always been very, very special. When you get a victory to share, it’s always better to have a team to share it with. So it’s what was the most attractive part and when we started discussions it gets to a point where even though I’m ambitious, I’m not greedy. So there’s a give and take and the format is something that I can easily overlook, and I’m pretty sure I can learn to enjoy it, I’ll just have to get used to it, but I’m pretty sure I’ll learn to enjoy it. To be honest, the more I started thinking about it, the more I started thinking about my college days that were 3 day tournaments, 54 holes, and everybody warmed up together for the most part. So it shouldn’t be an environment I’m unfamiliar with.” This is from the LIV podcast called “Fairway to Heaven”. Full link:

Jon Rahm on the LIV format: “Yeah, obviously there’s been a bit of a change. There was a lot more about LIV Golf that was attractive to me, right. Yeah, maybe the format was a set back in the past, but at the same time there’s a lot of positives to it as well. And one of the things that a lot of players kept mentioning is you don’t have a wave weather difference, where you can simply get unlucky and you’re out of contention for that tournament. It’s part of the game, I get it, but it’s something you don’t have to deal with anymore. So that part is a very nice aspect. The team is what really made it for me. Being able to be part of a team, represent a team, play for my teammates, with my teammates and against my teammates, is something that to me that has always been very, very special. When you get a victory to share, it’s always better to have a team to share it with. So it’s what was the most attractive part and when we started discussions it gets to a point where even though I’m ambitious, I’m not greedy. So there’s a give and take and the format is something that I can easily overlook, and I’m pretty sure I can learn to enjoy it, I’ll just have to get used to it, but I’m pretty sure I’ll learn to enjoy it. To be honest, the more I started thinking about it, the more I started thinking about my college days that were 3 day tournaments, 54 holes, and everybody warmed up together for the most part. So it shouldn’t be an environment I’m unfamiliar with.” This is from the LIV podcast called “Fairway to Heaven”. Full link:

Flushing It

562,892 görüntüleme • 2 yıl önce

GPT-5.6 Pro is insane. It didn’t just beat Claude 5, Fable and Mythos. It crushed them. One prompt, just 5 minutes. And voila: A full low-poly Three.js island game with water, beach bar, boat, shark, fish, whales, sports area, NPCs and Ibiza vibes This is getting ridiculous. That is what I would write if I was not honest with you. That is what I would post if I only wanted a viral clickbait tweet. And this is exactly why you should always be careful with what you read on social media, especially on X. There is no GPT-5.6 yet. This prototype was made with GPT-5.5, in 6 iterations, after more than 40 minutes of back-and-forth with Codex. Yes, it started with one prompt, and I will share that prompt below. But the final result came from many corrections, adjustments, fixes, visual tweaks, Three.js issues, camera changes, object placement improvements, and a lot of manual direction. That is the real workflow. I share build in public content here to show what you can actually do with AI, but also to show that there is no magic dust. AI is powerful. Very powerful. But the difference between a cool demo and a real usable prototype is still iteration, feedback, taste, debugging, and direction. Yes, I am also waiting for GPT-5.6. It will probably arrive next week, and when it does, we will test it here properly, in public, with real prompts, real iterations, and real results.

GPT-5.6 Pro is insane. It didn’t just beat Claude 5, Fable and Mythos. It crushed them. One prompt, just 5 minutes. And voila: A full low-poly Three.js island game with water, beach bar, boat, shark, fish, whales, sports area, NPCs and Ibiza vibes This is getting ridiculous. That is what I would write if I was not honest with you. That is what I would post if I only wanted a viral clickbait tweet. And this is exactly why you should always be careful with what you read on social media, especially on X. There is no GPT-5.6 yet. This prototype was made with GPT-5.5, in 6 iterations, after more than 40 minutes of back-and-forth with Codex. Yes, it started with one prompt, and I will share that prompt below. But the final result came from many corrections, adjustments, fixes, visual tweaks, Three.js issues, camera changes, object placement improvements, and a lot of manual direction. That is the real workflow. I share build in public content here to show what you can actually do with AI, but also to show that there is no magic dust. AI is powerful. Very powerful. But the difference between a cool demo and a real usable prototype is still iteration, feedback, taste, debugging, and direction. Yes, I am also waiting for GPT-5.6. It will probably arrive next week, and when it does, we will test it here properly, in public, with real prompts, real iterations, and real results.

Givros

60,868 görüntüleme • 21 gün önce

Sam Altman on GPT 5: "This morning I was testing our new model and I got a question. I got emailed a question that I didn't quite understand. And I put it in the model, this is GPT-5, and it answered it perfectly. And I really kind of sat back in my chair and I was just like, oh man, here it is moment... I felt like useless relative to the AI in this thing that I felt like I should have been able to do and I couldn't. It was really hard. But the AI just did it like that. It was a weird feeling."

Sam Altman on GPT 5: "This morning I was testing our new model and I got a question. I got emailed a question that I didn't quite understand. And I put it in the model, this is GPT-5, and it answered it perfectly. And I really kind of sat back in my chair and I was just like, oh man, here it is moment... I felt like useless relative to the AI in this thing that I felt like I should have been able to do and I couldn't. It was really hard. But the AI just did it like that. It was a weird feeling."

Chris

5,664,499 görüntüleme • 11 ay önce

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 görüntüleme • 4 ay önce

I kind of like Gemini 3.0 Flash in Antigravity. It is fast, and the Browser Subagent works great with it. A few days ago, I asked it to rebuild my website entirely based on the existing codebase. It redesigned everything and tested it too. I did not have much time for iteration, but it was good enough, and I deployed it.

I kind of like Gemini 3.0 Flash in Antigravity. It is fast, and the Browser Subagent works great with it. A few days ago, I asked it to rebuild my website entirely based on the existing codebase. It redesigned everything and tested it too. I did not have much time for iteration, but it was good enough, and I deployed it.

AshutoshShrivastava

41,433 görüntüleme • 6 ay önce

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.

Peter Gostev

262,507 görüntüleme • 2 ay önce

Nobody seems to know how insane GPT-5.4 is with computer use. I asked GPT-5.4 to draw the OpenAI logo in Microsoft Paint. No computer use API. Just a screenshot and basic tool calls (click, drag, press_key) all coordinate-based. The first drawing was awful. And GPT knew it. It looked at its own result and essentially went "yeah, no." What happened next is what broke my brain: It opened a browser. Went to Bing Images. Searched for the OpenAI logo. Found one. Then (and I cannot stress this enough) it used the Windows area screenshot shortcut (Win+Shift+S) to snip just the logo off the screen. Went back to Paint. Imported it. Centered it. All on its own. No instructions to do any of that. It just improvised a better strategy when the first one failed. My prompt was "Draw the OpenAI logo" with Paint already opened on the computer. Sure, it's "cheating." But honestly? That's exactly what I'd do too. And the fact that it came up with this plan from nothing but a screenshot and a coordinate system is wild.

Clad3815

1,069,256 görüntüleme • 4 ay önce

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a LIVING system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Yam Peleg

419,504 görüntüleme • 6 ay önce

.Erik Voorhees: It’s actually good, from the Trojan horse perspective, that Bitcoin was traceable enough for traditional institutions to tolerate it. “When Bitcoin came out, everyone called it private, thought of it as private. It was referred to as anonymous in every news story. And in some ways, it is very private and very anonymous. But the truth is that it’s also extremely trackable and traceable. It is not private in reality. And the question is, should it have been from the start? And at first I thought, yes, it should have been more private. And that was a mistake in its design. However, I think if Bitcoin had been anonymous truly from the start, like a Zcash or a Monero, it would have had such antagonism from the state. I don’t know that the state could have snuffed it out, but they would have tried much harder. And I think it’s actually good, from the Trojan horse metaphor perspective, that it was traceable enough that the traditional institutions could tolerate it. They’ve never liked it, but they could at least tolerate it because there is some traceability. And that has allowed Bitcoin to grow. And I think in its shadow, that other crypto assets are actually anonymous is very healthy. The strength of cryptocurrency as a concept in society, I think, is served best when Bitcoin itself is not perfectly private, but other assets are. That is a very difficult thing, I think, for the state to combat. And that decentralization of attributes is really, really crucial. So, yeah, I’m very glad that there are other coins that are private. I want there to be more of them, and I want them to be more popular. And I think it’s okay that Bitcoin itself is not.”

.Erik Voorhees: It’s actually good, from the Trojan horse perspective, that Bitcoin was traceable enough for traditional institutions to tolerate it. “When Bitcoin came out, everyone called it private, thought of it as private. It was referred to as anonymous in every news story. And in some ways, it is very private and very anonymous. But the truth is that it’s also extremely trackable and traceable. It is not private in reality. And the question is, should it have been from the start? And at first I thought, yes, it should have been more private. And that was a mistake in its design. However, I think if Bitcoin had been anonymous truly from the start, like a Zcash or a Monero, it would have had such antagonism from the state. I don’t know that the state could have snuffed it out, but they would have tried much harder. And I think it’s actually good, from the Trojan horse metaphor perspective, that it was traceable enough that the traditional institutions could tolerate it. They’ve never liked it, but they could at least tolerate it because there is some traceability. And that has allowed Bitcoin to grow. And I think in its shadow, that other crypto assets are actually anonymous is very healthy. The strength of cryptocurrency as a concept in society, I think, is served best when Bitcoin itself is not perfectly private, but other assets are. That is a very difficult thing, I think, for the state to combat. And that decentralization of attributes is really, really crucial. So, yeah, I’m very glad that there are other coins that are private. I want there to be more of them, and I want them to be more popular. And I think it’s okay that Bitcoin itself is not.”

Arjun Khemani

23,056 görüntüleme • 18 gün önce

My review of GOALS. At first, the dribbling felt a bit unusual and not quite as responsive as I expected. But the more I played, the more it started to click as I got used to the skill mechanics. By the end, I was scoring some really nice goals, so I can see it getting even better with more game time and improved squad. I really like the defending. Player switching feels great, and I think they've found a good balance with the double man press. It helps when needed but you still have to be active with the player you're controlling W! I also felt like opponents got punished for mistakes. At no point did it feel like the AI was automatically doing all the defending or suffocating the player.. W! I think the anti-possession mechanic to stop time-wasting is a little overkill and imo, a game like this doesn't really need it. The actual in game graphics could be a little better but the menus, concept art, and overall aesthetic are really clean. I love the look of it. The idea of building a 1 of 1 personalised club and having cards that can grow their overall rating is a really cool direction and I can definitely see it working well. There's still room for improvement but it's got a solid foundation to build on. Would I play it again? absolutely.

My review of GOALS. At first, the dribbling felt a bit unusual and not quite as responsive as I expected. But the more I played, the more it started to click as I got used to the skill mechanics. By the end, I was scoring some really nice goals, so I can see it getting even better with more game time and improved squad. I really like the defending. Player switching feels great, and I think they've found a good balance with the double man press. It helps when needed but you still have to be active with the player you're controlling W! I also felt like opponents got punished for mistakes. At no point did it feel like the AI was automatically doing all the defending or suffocating the player.. W! I think the anti-possession mechanic to stop time-wasting is a little overkill and imo, a game like this doesn't really need it. The actual in game graphics could be a little better but the menus, concept art, and overall aesthetic are really clean. I love the look of it. The idea of building a 1 of 1 personalised club and having cards that can grow their overall rating is a really cool direction and I can definitely see it working well. There's still room for improvement but it's got a solid foundation to build on. Would I play it again? absolutely.

Fuji

128,618 görüntüleme • 1 ay önce