Загрузка видео...

Не удалось загрузить видео

На главную

Why did spec-driven development never take off - the workflow tools like Amazon’s Kiro or GitHub Workspaces encouraged? dex, founder of HumanLayer: “These projects have a really interesting idea: you maintain a set of specifications for your software, and then you maintain the code itself, and the dream is...

Pragmatic_Eng's profile picture

The Pragmatic Engineer

48,688 subscribers

160,830 просмотров • 7 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Software development will never be the same. I want you to watch this video: This is a spec-driven development environment. 100% of your time goes to writing specs and managing agents. 0% goes to writing the code.
6:04

Software development will never be the same. I want you to watch this video: This is a spec-driven development environment. 100% of your time goes to writing specs and managing agents. 0% goes to writing the code.

Santiago

120,161 просмотров • 7 месяцев назад

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:
1:21

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

42,501 просмотров • 1 месяц назад

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."
2:04

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

The Pragmatic Engineer

39,011 просмотров • 2 месяцев назад

“Our biggest bottleneck is becoming the review of code, rather than the actual writing and generation of code.” Cisco CPO Jeetu Patel says code review is still super important though, because without human taste and judgment, code quickly turns into slop: “Every engineer on that team is now just a spec developer.” “They just build specs. They create markdown files. They give context to the model. They give context to the agent. And then the agent’s writing the code.” “I think, presumably, the review is going to get easier, too.” “You’ll have really crappy software that gets written if people aren’t paying attention to it. It doesn’t obviate the need for having taste, and having judgment, and having instinct, and making sure that you’re thinking about what you’re building."
1:35

“Our biggest bottleneck is becoming the review of code, rather than the actual writing and generation of code.” Cisco CPO Jeetu Patel says code review is still super important though, because without human taste and judgment, code quickly turns into slop: “Every engineer on that team is now just a spec developer.” “They just build specs. They create markdown files. They give context to the model. They give context to the agent. And then the agent’s writing the code.” “I think, presumably, the review is going to get easier, too.” “You’ll have really crappy software that gets written if people aren’t paying attention to it. It doesn’t obviate the need for having taste, and having judgment, and having instinct, and making sure that you’re thinking about what you’re building."

TBPN

11,289 просмотров • 5 месяцев назад

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.
1:19

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

124,508 просмотров • 1 месяц назад

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.
1:00

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

Kyle Walker

13,740 просмотров • 23 дней назад

Claude Code documentation agent keeps project docs up to date with Docusaurus. Created a Docusaurus site: npx create-docusaurus@latest my-docs classic Added the agent: npx claude-code-templates@latest --agent=documentation/docusaurus-expert --yes Then prompt: "Use docusaurus-expert to review that the documentation is correct and up-to-date" Now the docs stay synced with code changes. That’s how I set up as shown in the video.
0:40

Claude Code documentation agent keeps project docs up to date with Docusaurus. Created a Docusaurus site: npx create-docusaurus@latest my-docs classic Added the agent: npx claude-code-templates@latest --agent=documentation/docusaurus-expert --yes Then prompt: "Use docusaurus-expert to review that the documentation is correct and up-to-date" Now the docs stay synced with code changes. That’s how I set up as shown in the video.

Daniel San

68,554 просмотров • 10 месяцев назад

here's how I generate beautiful emails using Paper and claude code for humblytics 1) I scraped all of our existing emails and outlined in our obsidian notes 2) ran my marketing-strategist skill to analzye existing open/close rates, pull context from our app and rewrite the entire email 3) connect to the paper mcp, open up claude code, and reference the new emails it just rewrote 4) design the entire email in paper, refine it, then when you're done ask claude code to export is as a .mjml file 5) load the .mjml file and you're done you now have emails that are on brand and designed to your specs
5:40

here's how I generate beautiful emails using Paper and claude code for humblytics 1) I scraped all of our existing emails and outlined in our obsidian notes 2) ran my marketing-strategist skill to analzye existing open/close rates, pull context from our app and rewrite the entire email 3) connect to the paper mcp, open up claude code, and reference the new emails it just rewrote 4) design the entire email in paper, refine it, then when you're done ask claude code to export is as a .mjml file 5) load the .mjml file and you're done you now have emails that are on brand and designed to your specs

amirmxt

11,222 просмотров • 3 месяцев назад

Indian developers are polluting everything this is what everyone will say, because of all these non-sense gitlab has conducted its hackathon and guess what all top 3 are indians, so naturally I was curious about the PRs that they have submitted and when i opened to see their contributions, all were just typo changes in the readme's, docu changes, docs, docs, docs, docs, docs only docs and grammatical fixes and not a single major code change or anything, not a real grade production code.. for these people a whole country will be ashamed ( let me put that on hold for a bit ) like... I mean, if they have to do this to add open source contributions to their CVs, then it's as good as you don't do open source at alI, it's a waste of time doing it like this
0:31

Indian developers are polluting everything this is what everyone will say, because of all these non-sense gitlab has conducted its hackathon and guess what all top 3 are indians, so naturally I was curious about the PRs that they have submitted and when i opened to see their contributions, all were just typo changes in the readme's, docu changes, docs, docs, docs, docs, docs only docs and grammatical fixes and not a single major code change or anything, not a real grade production code.. for these people a whole country will be ashamed ( let me put that on hold for a bit ) like... I mean, if they have to do this to add open source contributions to their CVs, then it's as good as you don't do open source at alI, it's a waste of time doing it like this

Humi

31,155 просмотров • 2 месяцев назад

Before software engineers even begin writing code, they have to set the stage of the entire development process. This process requires engineers to make complex tradeoffs between requirements, system design, and implementations details. Current IDEs that rely on AI features, like chat and inline coding, can help engineers get the job done quickly on small development tasks. Still, engineers spend much more time on larger projects—even after the initial code is generated—by conducting rigorous testing and creating documentation. This is where today’s AI IDEs can do more to accelerate the development lifecycle—and this is why we built Kiro. Kiro is an AI IDE that helps you go from prototype to production with spec-driven development and agent hooks. From simple to complex tasks, Kiro works alongside you to turn prompts into detailed specs, then into working code, docs, and test so what you build is exactly what you want and ready to share with your team. After a developer builds the code with Kiro, Kiro’s agent hooks help engineers solve challenging problems and automate tasks like generating documentation and unit tests. Kiro brings structure and mature engineering practices to AI coding, so you can go from concept to application while being in the driver’s seat every step of the way. Kiro is free during preview, and supports Mac, Windows, and Linux, and most popular programming languages. We're excited for you to try it out and let us know what you think ➡️
1:12

Before software engineers even begin writing code, they have to set the stage of the entire development process. This process requires engineers to make complex tradeoffs between requirements, system design, and implementations details. Current IDEs that rely on AI features, like chat and inline coding, can help engineers get the job done quickly on small development tasks. Still, engineers spend much more time on larger projects—even after the initial code is generated—by conducting rigorous testing and creating documentation. This is where today’s AI IDEs can do more to accelerate the development lifecycle—and this is why we built Kiro. Kiro is an AI IDE that helps you go from prototype to production with spec-driven development and agent hooks. From simple to complex tasks, Kiro works alongside you to turn prompts into detailed specs, then into working code, docs, and test so what you build is exactly what you want and ready to share with your team. After a developer builds the code with Kiro, Kiro’s agent hooks help engineers solve challenging problems and automate tasks like generating documentation and unit tests. Kiro brings structure and mature engineering practices to AI coding, so you can go from concept to application while being in the driver’s seat every step of the way. Kiro is free during preview, and supports Mac, Windows, and Linux, and most popular programming languages. We're excited for you to try it out and let us know what you think ➡️

Swami Sivasubramanian

154,343 просмотров • 1 год назад

Here is a demo of the most comprehensive research agent for your code docs, powered by Nozomio Labs. It turns your indexed repos and docs into a dynamic tree that the agent can access on the fly, using SOTA tools to reduce code hallucinations. Now using the latest Anthropic model, Claude Opus 4.5.
0:35

Here is a demo of the most comprehensive research agent for your code docs, powered by Nozomio Labs. It turns your indexed repos and docs into a dynamic tree that the agent can access on the fly, using SOTA tools to reduce code hallucinations. Now using the latest Anthropic model, Claude Opus 4.5.

Arlan

28,405 просмотров • 8 месяцев назад

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!
12:40

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

Sebastian Schöner

13,033 просмотров • 3 месяцев назад

every other day i yearn for more research fields to adopt the culture from the ML and ML adjacent fields of building a demo website for each paper and put code on github
0:48

every other day i yearn for more research fields to adopt the culture from the ML and ML adjacent fields of building a demo website for each paper and put code on github

outside five sigma

27,352 просмотров • 9 месяцев назад

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

62,825 просмотров • 2 месяцев назад

This might be the best "AI Engineer" I've tried so far. ​ I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. ​ I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. ​ Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. ​ I go into more details in the video, but here is the TLDR; ​ 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. ​ 2. Love the approach of generating a plan with sub-tasks before writing any code. ​ 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. ​ 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! ​ 5. It's fast. It runs locally. It's an extension to Visual Studio Code. ​ I'm impressed, but I don't think this tool is for me. ​ I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. ​ I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. ​ Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. ​ Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.
8:37

This might be the best "AI Engineer" I've tried so far. ​ I'm an old school developer who started 30 years ago. I feel very uncomfortable letting AI take control of my code, but for the sake of science, I spent two hours building an application that took me weeks to build a couple of years ago. ​ I used Pythagora, a brand new tool backed by Y Combinator. They just released to the public. ​ Keep in mind that I use AI every day to write code, but Pythagora is something different: it's a tool that leads, and uses you—the human—as the copilot. ​ I go into more details in the video, but here is the TLDR; ​ 1. Holy molly! We've made a ton of progress on this front! This is way better than Devin when I tested it a few months back. ​ 2. Love the approach of generating a plan with sub-tasks before writing any code. ​ 3. The tools never tries to do too much: it tackles every small task one at a time, and gives you instructions so you test everything. ​ 4. It does exactly what you'd do when it gets stuck: writes a bunch of logs and uses those to correct itself. Pretty neat! ​ 5. It's fast. It runs locally. It's an extension to Visual Studio Code. ​ I'm impressed, but I don't think this tool is for me. ​ I'm not the type of developer who's ready to relinquish control. I felt I had no connection with the code because I didn't write it. It was not my code. ​ I know many people who don't care about this. I know many people who will get tremendous value out of Pythagora. I hope they keep pushing the limits, providing feedback, and helping this get to a point where old folks like me feel more comfortable using it. ​ Don't take my word for it. The best thing you can do is to give it a try and see how you feel using it. ​ Thanks to the team who built this, for all of the explanations and support, and especially, for sitting and listening to my dumb questions for 2 hours while I tested this.

Santiago

212,056 просмотров • 1 год назад

do you have an interesting yet simple idea that you can't get claude code / codex to build? if so, I want to hear it or see a sketch, and then try building a decent start for you. I need little distractions when I'm tired of working on my own projects that never end. the end result would be an open source code artifact, and I'll do my best to include prompts/process where possible. video is the quintessential example, time-helix built from a Tim Babb sketch/idea
0:33

do you have an interesting yet simple idea that you can't get claude code / codex to build? if so, I want to hear it or see a sketch, and then try building a decent start for you. I need little distractions when I'm tired of working on my own projects that never end. the end result would be an open source code artifact, and I'll do my best to include prompts/process where possible. video is the quintessential example, time-helix built from a Tim Babb sketch/idea

Codetaur

24,190 просмотров • 2 месяцев назад

Ever seen a fresh (20x) Claude Max account's 5-hour usage allowance get drained in ~14 minutes? Feast your eyes on my bizarre life now with this screen recording of a recent live work session, something I've gotten at least 100 requests for over the past month. Maybe you can understand now why I need so many accounts and how I can work on so many different projects. You can also see the truth of what I was saying recently about how, once your plan is done and the beads made and polished, it's mostly just machine-tending the swarm that doesn't require much thought. Lots of just telling it to get the next bead and work on it, to review code, to re-read AGENTS dot md after a compaction, etc. And you can see how I use gemini-cli for code review. I give Google a lot of crap for the harness being broken and the capacity overloads, but when it works, it's actually really good for this code review use case. I don't usually let it write new code, though, because I think Opus and 5.2 do a better job. Also, sorry the recording is a bit blurry; I have a 5K resolution monitor and screen recordings usually are hard to watch from it. And btw, this really wasn't that normal of a session for me, it was more frenetic than usual, because I don't want to dox myself or my clients by accident. Hence all the ceaseless terminal tab swirling. I usually do more planning work while this stuff is going on, but I wanted to minimize the chances of leaking important information. That's also why I didn't refresh the Gemini login in the WezTerm window, which killed me, trust me. It's the reason I hate doing these screen recordings in the first place; it kills my productivity. Anyway, hope you liked it. I will also post to YouTube, see reply for link. Thanks for watching.
14:24

Ever seen a fresh (20x) Claude Max account's 5-hour usage allowance get drained in ~14 minutes? Feast your eyes on my bizarre life now with this screen recording of a recent live work session, something I've gotten at least 100 requests for over the past month. Maybe you can understand now why I need so many accounts and how I can work on so many different projects. You can also see the truth of what I was saying recently about how, once your plan is done and the beads made and polished, it's mostly just machine-tending the swarm that doesn't require much thought. Lots of just telling it to get the next bead and work on it, to review code, to re-read AGENTS dot md after a compaction, etc. And you can see how I use gemini-cli for code review. I give Google a lot of crap for the harness being broken and the capacity overloads, but when it works, it's actually really good for this code review use case. I don't usually let it write new code, though, because I think Opus and 5.2 do a better job. Also, sorry the recording is a bit blurry; I have a 5K resolution monitor and screen recordings usually are hard to watch from it. And btw, this really wasn't that normal of a session for me, it was more frenetic than usual, because I don't want to dox myself or my clients by accident. Hence all the ceaseless terminal tab swirling. I usually do more planning work while this stuff is going on, but I wanted to minimize the chances of leaking important information. That's also why I didn't refresh the Gemini login in the WezTerm window, which killed me, trust me. It's the reason I hate doing these screen recordings in the first place; it kills my productivity. Anyway, hope you liked it. I will also post to YouTube, see reply for link. Thanks for watching.

Jeffrey Emanuel

86,071 просмотров • 6 месяцев назад

Richard Fleischer on how he directs a movie: "Interviewer: How do you work once you’re on the set? Do you have a specific approach? Fleischer: When you’re a director, you’re not only dealing with the actors, but everything needs your full attention at the same time, and that’s what I do for a living: I give a hundred and ten percent of my time and energy and have thought about the things that I am working on, and hopefully, there’s a way to cope with every element you have to deal with. After coming home from the studio in the evening, I plan the next day’s work and layout a plan of action for the blocking of the scenes. I try to block them in my mind before I get to the stage, the position of the actors and where will the camera be. However, when I get to the set, I try not to let the actors know that I have already planned it, I let them feel their way around, and by making slight suggestions, it comes out the way I want it to come out. But the actors feel they have contributed to the direction of the scene, which is what I want. So I am helping them find their way, that’s one of the things. Suppose you’re working on a scene that has already been blocked, or partly shot or well-rehearsed, then I have to figure out the order of shooting: what do I shoot first, second, third… and make a list of every setup I have to make in the order of shooting, not necessarily in the order of continuity. You try to find the most economical way to shoot a picture; for instance, if you got a scene where people are making a lot of entrances and exits through a door, but they’re separated in different parts of the film, you work it out so you shoot all of those doorway scenes one after the other and you save a lot of time. You don’t have to take down the lighting and everything else. However, if it interrupts the flow, if the actors kind of get lost in the scene they’re doing, then I stop that, and I’d have to do it the other way. But mostly, it’s a matter of deciding what you want to shoot the next day and in what order." (Richard Fleischer: “Orson Welles changed everything for everybody”, Film Talk, 2003) Clip from: See No Evil (1971) Director: Richard Fleischer
1:31

Richard Fleischer on how he directs a movie: "Interviewer: How do you work once you’re on the set? Do you have a specific approach? Fleischer: When you’re a director, you’re not only dealing with the actors, but everything needs your full attention at the same time, and that’s what I do for a living: I give a hundred and ten percent of my time and energy and have thought about the things that I am working on, and hopefully, there’s a way to cope with every element you have to deal with. After coming home from the studio in the evening, I plan the next day’s work and layout a plan of action for the blocking of the scenes. I try to block them in my mind before I get to the stage, the position of the actors and where will the camera be. However, when I get to the set, I try not to let the actors know that I have already planned it, I let them feel their way around, and by making slight suggestions, it comes out the way I want it to come out. But the actors feel they have contributed to the direction of the scene, which is what I want. So I am helping them find their way, that’s one of the things. Suppose you’re working on a scene that has already been blocked, or partly shot or well-rehearsed, then I have to figure out the order of shooting: what do I shoot first, second, third… and make a list of every setup I have to make in the order of shooting, not necessarily in the order of continuity. You try to find the most economical way to shoot a picture; for instance, if you got a scene where people are making a lot of entrances and exits through a door, but they’re separated in different parts of the film, you work it out so you shoot all of those doorway scenes one after the other and you save a lot of time. You don’t have to take down the lighting and everything else. However, if it interrupts the flow, if the actors kind of get lost in the scene they’re doing, then I stop that, and I’d have to do it the other way. But mostly, it’s a matter of deciding what you want to shoot the next day and in what order." (Richard Fleischer: “Orson Welles changed everything for everybody”, Film Talk, 2003) Clip from: See No Evil (1971) Director: Richard Fleischer

DepressedBergman

142,398 просмотров • 7 месяцев назад