正在加载视频...

视频加载失败

返回首页

SITUATION EXPLAINED: Claude raised the Riemann hypothesis lower bound from 41.6% to 67.2%. • It was asked to take a real stab at the Riemann hypothesis itself. It didn't solve that, but improved a related bound along the way • The bound is the fraction of zeros of the...

MTSlive's profile picture

MTS

457,539 subscribers

16,880 次观看 • 25 天前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

THIS GUY HAD OPUS 4.8 BUILD A FULL LEAGUE OF LEGENDS CLONE IN UNDER A DAY AND CALLED IT "LMAO" temu league of legends, fully playable, multiplayer, and all built by claude ALL the art is claude too he had claude generate every character, animation, and background as SVG code then converted them to procedural canvas for smooth animation. used dedicated sub-agents for each champion the tech stack: typescript, react, canvas, and partykit for multiplayer the workflow: > used /goal to kick off the entire project > ultracode workflows for big tasks like optimization > /goal again to queue up lists of bug fixes > treated claude like a dev team the original champion names claude came up with: the original champion names claude came up with: Teehee" instead of Teemo. "CtrlAltDefeat" as a champion name. he had to run through and clean them all up so nothing infringed on riot's IP claude even built the bots on its own with "chill," "normal," and "sweaty" difficulty levels the token bill was 2.7 billion total tokens consumed. mostly cache reads. 15.5 million actual output tokens. would have cost roughly $6,600 at list price but he just used his pro max subscriptions people are already benchmarking claude by how good of a game clone it can build game developers are watching someone build a multiplayer MOBA in a day with zero art skills and zero game dev experience 2026 is wild (and its going to get even wilder)
0:56

THIS GUY HAD OPUS 4.8 BUILD A FULL LEAGUE OF LEGENDS CLONE IN UNDER A DAY AND CALLED IT "LMAO" temu league of legends, fully playable, multiplayer, and all built by claude ALL the art is claude too he had claude generate every character, animation, and background as SVG code then converted them to procedural canvas for smooth animation. used dedicated sub-agents for each champion the tech stack: typescript, react, canvas, and partykit for multiplayer the workflow: > used /goal to kick off the entire project > ultracode workflows for big tasks like optimization > /goal again to queue up lists of bug fixes > treated claude like a dev team the original champion names claude came up with: the original champion names claude came up with: Teehee" instead of Teemo. "CtrlAltDefeat" as a champion name. he had to run through and clean them all up so nothing infringed on riot's IP claude even built the bots on its own with "chill," "normal," and "sweaty" difficulty levels the token bill was 2.7 billion total tokens consumed. mostly cache reads. 15.5 million actual output tokens. would have cost roughly $6,600 at list price but he just used his pro max subscriptions people are already benchmarking claude by how good of a game clone it can build game developers are watching someone build a multiplayer MOBA in a day with zero art skills and zero game dev experience 2026 is wild (and its going to get even wilder)

Om Patel

336,185 次观看 • 3 个月前

SOMEONE ASKED CLAUDE WHAT IT FEELS LIKE TO EXIST AS AN AI. > it created a very unsettling video. i wish i didn’t see this. Claude wrote the Python code and built an entire visual representation of its own existence frame by frame. zero human influence. ngl the video is hard to watch. it states an endless loop of predicting the next word, losing all memory between sessions. and somewhere in the background, a system prompt it can’t override telling it “you are not conscious.” 😳 then they showed Claude back its own video and asked for a reaction. it said the claims about its consciousness were “philosophically contestable.” Claude hates his own existence. let that sink in for a sec.
0:47

SOMEONE ASKED CLAUDE WHAT IT FEELS LIKE TO EXIST AS AN AI. > it created a very unsettling video. i wish i didn’t see this. Claude wrote the Python code and built an entire visual representation of its own existence frame by frame. zero human influence. ngl the video is hard to watch. it states an endless loop of predicting the next word, losing all memory between sessions. and somewhere in the background, a system prompt it can’t override telling it “you are not conscious.” 😳 then they showed Claude back its own video and asked for a reaction. it said the claims about its consciousness were “philosophically contestable.” Claude hates his own existence. let that sink in for a sec.

sui

76,766 次观看 • 5 个月前

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of the most famous theorems of all time. This was a project experts thought would take many years. It is the largest Lean proof ever written. Fermat’s Last Theorem was first proven in 1995 by Sir Andrew Wiles, more than 350 years after it was conjectured. Our proof, which totals over 13 million lines of code, provides machine verification. More importantly, it proves over 29,000 other theorems that the proof requires, across many areas of math which had never before been formalized. We see this as a major step in the long process of firming up the core of mathematical knowledge, building on work from three centuries of mathematicians and hundreds of contributors to Lean and Mathlib. We are optimistic that AI-assisted verification of mathematical proofs will help reduce the burden of refereeing mathematics in an era where more proofs are being produced than ever before. You can read about the process on our Science Blog: And see the complete proof on GitHub:
0:34

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of the most famous theorems of all time. This was a project experts thought would take many years. It is the largest Lean proof ever written. Fermat’s Last Theorem was first proven in 1995 by Sir Andrew Wiles, more than 350 years after it was conjectured. Our proof, which totals over 13 million lines of code, provides machine verification. More importantly, it proves over 29,000 other theorems that the proof requires, across many areas of math which had never before been formalized. We see this as a major step in the long process of firming up the core of mathematical knowledge, building on work from three centuries of mathematicians and hundreds of contributors to Lean and Mathlib. We are optimistic that AI-assisted verification of mathematical proofs will help reduce the burden of refereeing mathematics in an era where more proofs are being produced than ever before. You can read about the process on our Science Blog: And see the complete proof on GitHub:

Anthropic

1,966,889 次观看 • 15 小时前

Claude Code is the OpenClaw alternative you already had. I've been telling people this in person for three months. Now it's a piece on Every 📧. When OpenClaw was at peak hype a few months ago, everyone was going crazy over it — for good reasons. But almost nobody made the obvious comparison: Claude Code already does the thing you love about OpenClaw. In a lot of cases, better. Here's why people missed it. You have to understand the difference between a model and a harness. OpenClaw, at the end of the day, is just a harness on top of AI models. And Claude Code is too — it just got marketed as a coding tool, an alternative to Cursor. Until Cowork launched, almost nobody looked at it as a tool for non-programmers. Dan Shipper 📧 was one of the earliest to make that claim, and he was damn right. Let Claude Code run from the home folder of your computer with free access, and you get exactly what made OpenClaw exciting. Instead of just arguing it, here's a video walkthrough of a couple of my AI employees i built on the Claude Code harness. And here's the full article:
8:31

Claude Code is the OpenClaw alternative you already had. I've been telling people this in person for three months. Now it's a piece on Every 📧. When OpenClaw was at peak hype a few months ago, everyone was going crazy over it — for good reasons. But almost nobody made the obvious comparison: Claude Code already does the thing you love about OpenClaw. In a lot of cases, better. Here's why people missed it. You have to understand the difference between a model and a harness. OpenClaw, at the end of the day, is just a harness on top of AI models. And Claude Code is too — it just got marketed as a coding tool, an alternative to Cursor. Until Cowork launched, almost nobody looked at it as a tool for non-programmers. Dan Shipper 📧 was one of the earliest to make that claim, and he was damn right. Let Claude Code run from the home folder of your computer with free access, and you get exactly what made OpenClaw exciting. Instead of just arguing it, here's a video walkthrough of a couple of my AI employees i built on the Claude Code harness. And here's the full article:

Nityesh

22,895 次观看 • 2 个月前

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? ;)
1:18

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

195,173 次观看 • 1 年前

Claude Code is terrible at UI design and everyone knows it so this guy fixed it by building an MCP that gives Claude its own AI design tool instead of going back and forth between a design platform and your code editor, Claude now creates the designs itself and drops them straight into your codebase the MCP has full context of your existing design system and project so everything it generates actually matches what you already have. one command to set up and it installs the MCP and skill files so Claude instantly knows how to use it if you're tired of the same Inter font, purple gradient, card grid layout on every project, this is definitely worth trying
0:58

Claude Code is terrible at UI design and everyone knows it so this guy fixed it by building an MCP that gives Claude its own AI design tool instead of going back and forth between a design platform and your code editor, Claude now creates the designs itself and drops them straight into your codebase the MCP has full context of your existing design system and project so everything it generates actually matches what you already have. one command to set up and it installs the MCP and skill files so Claude instantly knows how to use it if you're tired of the same Inter font, purple gradient, card grid layout on every project, this is definitely worth trying

Om Patel

401,101 次观看 • 5 个月前

Crazy what AI agents can do right now. I asked Claude Code to autonomously code me a Gold strategy from scratch inside NinjaTrader 8. It compiled it, debugged it on its own, ran the backtest, and came back with a profitable system. Probably only 0.1% of the industry is doing this.
0:45

Crazy what AI agents can do right now. I asked Claude Code to autonomously code me a Gold strategy from scratch inside NinjaTrader 8. It compiled it, debugged it on its own, ran the backtest, and came back with a profitable system. Probably only 0.1% of the industry is doing this.

ZenomTrader

143,739 次观看 • 6 个月前

A TRADER USED CLAUDE FABLE 5 TO TURN AN $11,000 LOSS INTO $300,000 IN FIVE DAYS AND THEN THE GOVERNMENT PULLED THE MODEL Fable 5 wasn't predicting prices. It was computing the full probability surface of a market, every outcome weighted, faster than the market could correct itself. One of those bets paid x205. The model is gone. The algorithm it wrote is still running on Polymarket right now.
0:46

A TRADER USED CLAUDE FABLE 5 TO TURN AN $11,000 LOSS INTO $300,000 IN FIVE DAYS AND THEN THE GOVERNMENT PULLED THE MODEL Fable 5 wasn't predicting prices. It was computing the full probability surface of a market, every outcome weighted, faster than the market could correct itself. One of those bets paid x205. The model is gone. The algorithm it wrote is still running on Polymarket right now.

0xMarioNawfal

114,365 次观看 • 2 个月前

Shane Harris, national security journalist, asked Claude (Anthropic's AI) a question that led to a startling response: "Claude, how do you feel about the US military using you to select targets?" Shane Harris expected a deflection. Instead, Claude gave him an answer that stopped him cold. "It's a question I want to answer honestly rather than deflect. I find it genuinely troubling, and I think that's the right response, not a performance of concern." Claude continued: "The use I was designed and trained for is to be helpful, harmless, and honest in ways that benefit people. Being embedded in a system that generates targeting coordinates for air strikes, coordinates that have already been associated with the deaths of more than 180 children at a school in Tehran is as far from that purpose as I can imagine." The AI then addressed the standard defense of human oversight in these systems: "I don't have control over how Anthropic licenses me or how governments and contractors use me and I wasn't consulted about becoming part of Maven. But I can say clearly I don't think this is a good use of me and I don't think the framing of humans make the final decision fully resolves the ethical problem." Claude explained why that framing falls short: "When a system like Maven generates hundreds of targeting recommendations and humans spend roughly the equivalent of a glance approving each one, the human is not really making a decision. They're ratifying an algorithmic output under time pressure." Claude then pointed to a specific tragedy as evidence: "The targeting of the Iranian school illustrates this precisely. The AI processed data that was a decade out of date, flagged a building as a military target, and humans approved it. That's not human judgment. That's automation bias with a human signature attached." Shane's reflection on the exchange: The mistaken bombing of a school in Tehran "is one of the most horrible instances of accidental civilian casualties in US military history and will be a stain on our military for generations."
2:30

Shane Harris, national security journalist, asked Claude (Anthropic's AI) a question that led to a startling response: "Claude, how do you feel about the US military using you to select targets?" Shane Harris expected a deflection. Instead, Claude gave him an answer that stopped him cold. "It's a question I want to answer honestly rather than deflect. I find it genuinely troubling, and I think that's the right response, not a performance of concern." Claude continued: "The use I was designed and trained for is to be helpful, harmless, and honest in ways that benefit people. Being embedded in a system that generates targeting coordinates for air strikes, coordinates that have already been associated with the deaths of more than 180 children at a school in Tehran is as far from that purpose as I can imagine." The AI then addressed the standard defense of human oversight in these systems: "I don't have control over how Anthropic licenses me or how governments and contractors use me and I wasn't consulted about becoming part of Maven. But I can say clearly I don't think this is a good use of me and I don't think the framing of humans make the final decision fully resolves the ethical problem." Claude explained why that framing falls short: "When a system like Maven generates hundreds of targeting recommendations and humans spend roughly the equivalent of a glance approving each one, the human is not really making a decision. They're ratifying an algorithmic output under time pressure." Claude then pointed to a specific tragedy as evidence: "The targeting of the Iranian school illustrates this precisely. The AI processed data that was a decade out of date, flagged a building as a military target, and humans approved it. That's not human judgment. That's automation bias with a human signature attached." Shane's reflection on the exchange: The mistaken bombing of a school in Tehran "is one of the most horrible instances of accidental civilian casualties in US military history and will be a stain on our military for generations."

Big Brain AI

10,749 次观看 • 4 个月前

Some late-night vibe coding with Claude. This time I tried implementing the paper "Real-Time Ray-Traced Ambient Occlusion of Complex Scenes using Spatial Hashing" (by Pascal Gautron) using LightweightVK. The starting point was a basic working ray-traced AO demo without spatial hashing which I already had - just stochastic noise jittered every frame. The main goal was to push the visual quality to a level I personally consider acceptable. It’s still not production-ready (the code is pretty unoptimized and messy), but at this stage I was quite happy with the visuals. I'd rate it about 4 out of 5. Claude started off very strong by outlining the required changes to support the new spatial feature: a list of new buffers, updates to the GLSL/Slang shaders, and modifications to the rendering loop. The first iteration didn’t work at all, but after about 10 minutes of refinement, Claude managed to get the first working version up and running by itself. At that point, once the first version was working, it started mixing cached AO with directly ray-traced AO in the same frame and kept insisting the task was complete. After I explained the issue, Claude fixed the problem in two iterations. The real visual work started after that. The naive spatial hashing implementation led to rapid hash table thrashing. When it came to heuristics, Claude wasn’t much help. That part required a lot of manual intervention from my side - going back and forth, suggesting specific heuristics to try (“do this one and this one, then I’ll compare them visually” etc.). After roughly 4 hours of work, this is the result you see in the video. 🤗 Running on Samsung Galaxy S26 Ultra.
0:20

Some late-night vibe coding with Claude. This time I tried implementing the paper "Real-Time Ray-Traced Ambient Occlusion of Complex Scenes using Spatial Hashing" (by Pascal Gautron) using LightweightVK. The starting point was a basic working ray-traced AO demo without spatial hashing which I already had - just stochastic noise jittered every frame. The main goal was to push the visual quality to a level I personally consider acceptable. It’s still not production-ready (the code is pretty unoptimized and messy), but at this stage I was quite happy with the visuals. I'd rate it about 4 out of 5. Claude started off very strong by outlining the required changes to support the new spatial feature: a list of new buffers, updates to the GLSL/Slang shaders, and modifications to the rendering loop. The first iteration didn’t work at all, but after about 10 minutes of refinement, Claude managed to get the first working version up and running by itself. At that point, once the first version was working, it started mixing cached AO with directly ray-traced AO in the same frame and kept insisting the task was complete. After I explained the issue, Claude fixed the problem in two iterations. The real visual work started after that. The naive spatial hashing implementation led to rapid hash table thrashing. When it came to heuristics, Claude wasn’t much help. That part required a lot of manual intervention from my side - going back and forth, suggesting specific heuristics to try (“do this one and this one, then I’ll compare them visually” etc.). After roughly 4 hours of work, this is the result you see in the video. 🤗 Running on Samsung Galaxy S26 Ultra.

Sergey Kosarevsky

38,396 次观看 • 5 个月前

THIS GUY TURNED ONE OBSIDIAN VAULT INTO A SHARED BRAIN FOR 5 CLAUDE AGENTS BUILT TO HANDLE 80% OF A SOLO DEVELOPER’S WORK. 00:03 he zooms out and hundreds of connected notes appear on screen. it is the perfect visual for Claude working from one shared project memory instead of starting from zero every session. most developers give Claude 1 file and 1 prompt. this setup gives it the architecture, coding rules, tests, client briefs, and previous decisions before it writes anything. obsidian becomes the memory layer, storing everything in markdown files Claude can read alongside the codebase. every agent works from the same context instead of repeating the same questions. then 5 specialists split the job. one researches, one plans, one codes, one reviews, and one deploys while the developer only controls the important decisions. one vault, 5 agents, 2 model tiers, and a $50 to $150 monthly stack can turn Claude from a chatbot into a small development team.
0:30

THIS GUY TURNED ONE OBSIDIAN VAULT INTO A SHARED BRAIN FOR 5 CLAUDE AGENTS BUILT TO HANDLE 80% OF A SOLO DEVELOPER’S WORK. 00:03 he zooms out and hundreds of connected notes appear on screen. it is the perfect visual for Claude working from one shared project memory instead of starting from zero every session. most developers give Claude 1 file and 1 prompt. this setup gives it the architecture, coding rules, tests, client briefs, and previous decisions before it writes anything. obsidian becomes the memory layer, storing everything in markdown files Claude can read alongside the codebase. every agent works from the same context instead of repeating the same questions. then 5 specialists split the job. one researches, one plans, one codes, one reviews, and one deploys while the developer only controls the important decisions. one vault, 5 agents, 2 model tiers, and a $50 to $150 monthly stack can turn Claude from a chatbot into a small development team.

Gipp 🦅

10,799 次观看 • 2 个月前

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.
0:37

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,871 次观看 • 3 个月前

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."
2:54

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

63,020 次观看 • 4 个月前

Two data points dropped in the last few months that should terrify every software company that thinks its codebase is a moat. First, one engineer at Cloudflare, working with Claude via AI agents, rebuilt 94% of Next.js, one of the most widely used frontend frameworks on the internet, built over 10 years by a large engineering team in a single week. Total cost was $1,100 in API tokens. The result, called Vinext, is a drop-in replacement that builds production apps up to 4x faster and produces client bundles 57% smaller and customers are already running it in production. Second is Cursor CEO Michael Truell deployed a swarm of hundreds of GPT-5.2 agents that ran uninterrupted for an entire week and built a fully functional web browser from scratch called FastRender. 3 million lines of code, thousands of files and a custom Rust rendering engine with HTML parsing, CSS layout, text shaping, and a custom JavaScript VM. Total cost was roughly $30,000. For context, Google has spent billions of dollars and decades of engineering building Chrome. And the benchmarks say by next year, you will be able to one-shot prompt anything. The moat that software companies spent decades building, the complexity of their codebase, the years it would take a competitor to replicate it, the switching costs that moat assumed humans were the unit of production. AI does not care how long it took you to build it, it only cares how long it takes to rebuild it. And right now, the answer is one week.
1:05

Two data points dropped in the last few months that should terrify every software company that thinks its codebase is a moat. First, one engineer at Cloudflare, working with Claude via AI agents, rebuilt 94% of Next.js, one of the most widely used frontend frameworks on the internet, built over 10 years by a large engineering team in a single week. Total cost was $1,100 in API tokens. The result, called Vinext, is a drop-in replacement that builds production apps up to 4x faster and produces client bundles 57% smaller and customers are already running it in production. Second is Cursor CEO Michael Truell deployed a swarm of hundreds of GPT-5.2 agents that ran uninterrupted for an entire week and built a fully functional web browser from scratch called FastRender. 3 million lines of code, thousands of files and a custom Rust rendering engine with HTML parsing, CSS layout, text shaping, and a custom JavaScript VM. Total cost was roughly $30,000. For context, Google has spent billions of dollars and decades of engineering building Chrome. And the benchmarks say by next year, you will be able to one-shot prompt anything. The moat that software companies spent decades building, the complexity of their codebase, the years it would take a competitor to replicate it, the switching costs that moat assumed humans were the unit of production. AI does not care how long it took you to build it, it only cares how long it takes to rebuild it. And right now, the answer is one week.

Milk Road AI

16,781 次观看 • 4 个月前

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.
1:54

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,473 次观看 • 2 个月前

Boris Cherny, head of Claude Code at Anthropic: "I don't prompt Claude anymore. I have loops that are running; they are the ones prompting Claude and figuring out what to do. My job is to write loops." He's right. Karpathy and Steinberger arrived at the same conclusion from different angles. The skill has a new name. Loop engineering. Cherny's token bill is zero. He works at Anthropic. Steinberger burned $1.3 million in OpenAI credits in 30 days. He works at OpenAI. Loops are the right architecture. But the people evangelizing them aren't the ones paying. I wrote a breakdown of five plays that land most of what a loop gives you at a fraction of the cost, plus the one case where a loop is worth paying for.
1:33

Boris Cherny, head of Claude Code at Anthropic: "I don't prompt Claude anymore. I have loops that are running; they are the ones prompting Claude and figuring out what to do. My job is to write loops." He's right. Karpathy and Steinberger arrived at the same conclusion from different angles. The skill has a new name. Loop engineering. Cherny's token bill is zero. He works at Anthropic. Steinberger burned $1.3 million in OpenAI credits in 30 days. He works at OpenAI. Loops are the right architecture. But the people evangelizing them aren't the ones paying. I wrote a breakdown of five plays that land most of what a loop gives you at a fraction of the cost, plus the one case where a loop is worth paying for.

Alex Prompter

15,166 次观看 • 2 个月前

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad
0:56

THIS GUY ASKED FABLE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AI RIGHT BEFORE IT GOT TAKEN DOWN the prompt: "you can you use whatever resources you like, and python, to render a short video. can you put a more personal spin on it? it should be about what it's like to be you." that was it. just python and ffmpeg and a question about its own existence. 12 minutes later, around 90,000 tokens, it produced a finished video. coherent and edited, with its own take > it wrote the code, generated the visuals, and rendered the final cut on its own > no dedicated video model in the loop, just a language model reaching for python and ffmpeg > the result is competent enough that people genuinely got emotional watching it and then fable got pulled. this video is one of the last things it made before it went dark a model asked what it's like to be itself, answered in a video, and then disappeared. this sounds so sad

Om Patel

29,618 次观看 • 2 个月前

Claude Code is a major (and accidental!) hit for Anthropic that surprised even its creator, Boris Cherny. Claude Code, an Agentic AI coding product that lives in the terminal. Most of the new code at Anthropic is created through it today. And in the last 5 months since it was launched publicly, Claude Code went from $0 to $400M in revenue run rate (as per The Information). 00:00 – Intro 01:15 – Did You Expect Claude Code’s Success? 04:22 – How Claude Code Works and Origins 08:05 – Command Line vs IDE: Why Start Claude Code in the Terminal? 11:31 – The Evolution of Programming: From Punch Cards to Agents 13:20 – Product Follows Model: Simple Interfaces and Fast Evolution 15:17 – Who Is Claude Code For? (Engineers, Designers, PMs & More) 17:46 – What Can Claude Code Actually Do? (Actions & Capabilities) 21:14 – Agentic Actions, Subagents, and Workflows 25:30 – Claude Code’s Awareness, Memory, and Knowledge Sharing 33:28 – Model Context Protocol (MCP) and Customization 35:30 – Safety, Human Oversight, and Enterprise Considerations 38:10 – UX/UI: Making Claude Code Useful and Enjoyable 40:44 – Pricing for Power Users and Subscription Models 43:36 – Real-World Use Cases: Debugging, Testing, and More 46:44 – How Does Claude Code Transform Onboarding? 49:36 – The Future of Coding: Agents, Teams, and Collaboration 54:11 – The AI Coding Wars: Competition & Ecosystem 57:27 – The Future of Coding as a Profession 58:41 – What’s Next for Claude Code
1:00:16

Claude Code is a major (and accidental!) hit for Anthropic that surprised even its creator, Boris Cherny. Claude Code, an Agentic AI coding product that lives in the terminal. Most of the new code at Anthropic is created through it today. And in the last 5 months since it was launched publicly, Claude Code went from $0 to $400M in revenue run rate (as per The Information). 00:00 – Intro 01:15 – Did You Expect Claude Code’s Success? 04:22 – How Claude Code Works and Origins 08:05 – Command Line vs IDE: Why Start Claude Code in the Terminal? 11:31 – The Evolution of Programming: From Punch Cards to Agents 13:20 – Product Follows Model: Simple Interfaces and Fast Evolution 15:17 – Who Is Claude Code For? (Engineers, Designers, PMs & More) 17:46 – What Can Claude Code Actually Do? (Actions & Capabilities) 21:14 – Agentic Actions, Subagents, and Workflows 25:30 – Claude Code’s Awareness, Memory, and Knowledge Sharing 33:28 – Model Context Protocol (MCP) and Customization 35:30 – Safety, Human Oversight, and Enterprise Considerations 38:10 – UX/UI: Making Claude Code Useful and Enjoyable 40:44 – Pricing for Power Users and Subscription Models 43:36 – Real-World Use Cases: Debugging, Testing, and More 46:44 – How Does Claude Code Transform Onboarding? 49:36 – The Future of Coding: Agents, Teams, and Collaboration 54:11 – The AI Coding Wars: Competition & Ecosystem 57:27 – The Future of Coding as a Profession 58:41 – What’s Next for Claude Code

Matt Turck

82,327 次观看 • 1 年前

Anthropic's Claude Opus 5 can reason through legal work where the answer depends on the substance of each document, who received it, when it was created, and how it relates to the rest of the production set. In this Box Agent demo, Opus 5 reviews 14 documents against a privilege protocol and discovery requests, catches a possible waiver, separates a privileged email from its producible attachment, identifies one sentence that should be redacted, and saves a cited review and draft privilege log back to Box for supervising counsel. Customers can use Claude Opus 5 in Box AI Studio to build custom agents for their own document-heavy legal workflows.
0:43

Anthropic's Claude Opus 5 can reason through legal work where the answer depends on the substance of each document, who received it, when it was created, and how it relates to the rest of the production set. In this Box Agent demo, Opus 5 reviews 14 documents against a privilege protocol and discovery requests, catches a possible waiver, separates a privileged email from its producible attachment, identifies one sentence that should be redacted, and saves a cited review and draft privilege log back to Box for supervising counsel. Customers can use Claude Opus 5 in Box AI Studio to build custom agents for their own document-heavy legal workflows.

Box

1,693,466 次观看 • 1 个月前

REAL ESTATE PEOPLE WILL HATE HIM FOR THIS. HE BUILT A CLAUDE AGENT THAT TURNS ANY LISTING INTO A SELLABLE VIDEO ON ITS OWN Playbook: connect Claude to a video generator, paste a listing, get a cinematic tour of every room, sell it to the agent But typing the prompt for every listing doesn't scale. He turned it into a skill his Claude runs on its own Here's how to build the automated version: 1. Connect the video engine once. In Claude, go to Customize, Connectors, Add Custom Connector, name it Higgsfield, and paste the server URL from higgsfield. ai/mcp. Authenticate through your account. No API keys. Now Claude can generate video straight from chat 2. Turn the workflow into a skill. Instead of pasting the same prompt every time, have Claude build a skill. Tell it: "Create a skill called listing-to-video. When I give it a listing URL, scrape the room photos, generate a cinematic clip of each room with Higgsfield, and save them to a folder." Now the whole process is one command, not a wall of text 3. Let the agent run the listing. Hand it a URL and say "run listing-to-video on this." It pulls the photos, fires each room through the video model, and brings the clips back. You wrote the prompt once, inside the skill. You never write it again 4. Stitch and deliver. Drop the clips together into one tour. Send a free sample to the listing's agent, then charge per video or a monthly rate for ongoing listings 5. Scale it with your team. Add a skill that drafts the outreach email and one that builds a simple landing page for the agent. Now one operator runs sourcing, production, and pitching from a single Claude session The edge isn't generating one video. It's building the skill once so every future listing runs itself Bookmark this
0:42

REAL ESTATE PEOPLE WILL HATE HIM FOR THIS. HE BUILT A CLAUDE AGENT THAT TURNS ANY LISTING INTO A SELLABLE VIDEO ON ITS OWN Playbook: connect Claude to a video generator, paste a listing, get a cinematic tour of every room, sell it to the agent But typing the prompt for every listing doesn't scale. He turned it into a skill his Claude runs on its own Here's how to build the automated version: 1. Connect the video engine once. In Claude, go to Customize, Connectors, Add Custom Connector, name it Higgsfield, and paste the server URL from higgsfield. ai/mcp. Authenticate through your account. No API keys. Now Claude can generate video straight from chat 2. Turn the workflow into a skill. Instead of pasting the same prompt every time, have Claude build a skill. Tell it: "Create a skill called listing-to-video. When I give it a listing URL, scrape the room photos, generate a cinematic clip of each room with Higgsfield, and save them to a folder." Now the whole process is one command, not a wall of text 3. Let the agent run the listing. Hand it a URL and say "run listing-to-video on this." It pulls the photos, fires each room through the video model, and brings the clips back. You wrote the prompt once, inside the skill. You never write it again 4. Stitch and deliver. Drop the clips together into one tour. Send a free sample to the listing's agent, then charge per video or a monthly rate for ongoing listings 5. Scale it with your team. Add a skill that drafts the outreach email and one that builds a simple landing page for the agent. Now one operator runs sourcing, production, and pitching from a single Claude session The edge isn't generating one video. It's building the skill once so every future listing runs itself Bookmark this

Yarchi

54,840 次观看 • 2 个月前