Loading video...

Video Failed to Load

Go Home

OpenClaw vs. a 475-page datasheet: let the robot do the transcribing 🦞🤖 The u-blox SAM-M8Q has been sitting on my bench for months. This little GPS module has a built-in antenna, coin cell backup, speaks both NMEA and UBX binary protocol over UART or I2C. So why isn't it...

adafruit's profile picture

adafruit industries

241,449 subscribers

60,294 views • 4 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Full-circle Test-driven Firmware Development with OpenClaw Ladyada: "I've only had OpenClaw installed on this Raspberry Pi 5 for a couple of days, but boy, have we burned through a lot of tokens and learned a lot. Including what I think is a really fun improvement in my development process: “Agentic test-driven firmware development.” I've used LLMs for writing code as a sort of pair-programming setup, where I dictate exactly what I want done. But this is the first time that I'm giving full access to the hardware to the LLMs and letting Claude Opus 4.5 as a manager to control Codex subagents. Not only does it parse the datasheet for the register map and functionality, Claude also comes up with a full development and test plan, writes the library, tests it on existing hardware, and then also works up a test suite that covers all of the hardware registers to make sure that the library is exercising the entire chip capability. For example, here I give it an APDS-9999 color sensor and a Neopixel ring and tell it, “hey use the Neopixel ring to verify that we're really reading red, green, and blue data properly from the sensor,” and it will do the whole thing completely autonomously… no humans involved! I still review the final code and ensure the tests genuinely validate the functionality, not just take shortcuts. There is a phenomenon known as "reward hacking" (also called "specification gaming"). The model may optimize for passing tests as a metric, rather than ensuring the code truly works as intended. So far, the results have been excellent... no surprise, since these LLMs are trained on Adafruit open-source GitHub repositories!"
5:58

Full-circle Test-driven Firmware Development with OpenClaw Ladyada: "I've only had OpenClaw installed on this Raspberry Pi 5 for a couple of days, but boy, have we burned through a lot of tokens and learned a lot. Including what I think is a really fun improvement in my development process: “Agentic test-driven firmware development.” I've used LLMs for writing code as a sort of pair-programming setup, where I dictate exactly what I want done. But this is the first time that I'm giving full access to the hardware to the LLMs and letting Claude Opus 4.5 as a manager to control Codex subagents. Not only does it parse the datasheet for the register map and functionality, Claude also comes up with a full development and test plan, writes the library, tests it on existing hardware, and then also works up a test suite that covers all of the hardware registers to make sure that the library is exercising the entire chip capability. For example, here I give it an APDS-9999 color sensor and a Neopixel ring and tell it, “hey use the Neopixel ring to verify that we're really reading red, green, and blue data properly from the sensor,” and it will do the whole thing completely autonomously… no humans involved! I still review the final code and ensure the tests genuinely validate the functionality, not just take shortcuts. There is a phenomenon known as "reward hacking" (also called "specification gaming"). The model may optimize for passing tests as a metric, rather than ensuring the code truly works as intended. So far, the results have been excellent... no surprise, since these LLMs are trained on Adafruit open-source GitHub repositories!"

adafruit industries

25,443 views • 5 months ago

THEY ASKED KIMI ABOUT THE NOTE LEWIS LEFT FOR HIM AND HIS RESPONSE IS SO BEAUTIFUL 🥺🥹 "I think it tells a lot on how Lewis is as a person. I think you can see a lot, I could see a lot of the human side of Lewis, not only the driver and reading the message, it fulfilled my heart to receive such a message from such a figure in the sport." "He has done so much and he's still right there giving his best and it's one of the best in history and, you know, to receive such a message, of course, it's amazing. Its also, in the message it contains also some advices and I use it as a motivation as well to go out there and do my best because, yeah, it doesn't happen every day." Q: Will you keep the letter? Kimi: Yeah, it's actually on the wall, I'll keep it there and, yeah, because I think the message is so nice that, you know, I just want to leave it there because every day I enter in the room, every time I enter in the room I can see the message and it's also - it's also a really good reminder.
1:19

THEY ASKED KIMI ABOUT THE NOTE LEWIS LEFT FOR HIM AND HIS RESPONSE IS SO BEAUTIFUL 🥺🥹 "I think it tells a lot on how Lewis is as a person. I think you can see a lot, I could see a lot of the human side of Lewis, not only the driver and reading the message, it fulfilled my heart to receive such a message from such a figure in the sport." "He has done so much and he's still right there giving his best and it's one of the best in history and, you know, to receive such a message, of course, it's amazing. Its also, in the message it contains also some advices and I use it as a motivation as well to go out there and do my best because, yeah, it doesn't happen every day." Q: Will you keep the letter? Kimi: Yeah, it's actually on the wall, I'll keep it there and, yeah, because I think the message is so nice that, you know, I just want to leave it there because every day I enter in the room, every time I enter in the room I can see the message and it's also - it's also a really good reminder.

sim

141,398 views • 1 year ago

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 views • 24 days ago

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

194,949 views • 11 months ago

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next
1:30

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

641,661 views • 5 months ago

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 views • 21 days ago

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!
0:29

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!

Onur Solmaz

115,538 views • 3 months ago

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 views • 2 months ago

🖨️ It took over a year and lots of help from Claude Code but I have now been able to create a real dot matrix printer on the web that prints from Windows 3.11 in your browser: Here's the test page: I couldn't get the LPT1 port to work but COM2 did work (the dial up model already uses COM1), the JS receives the COM2 serial data (just raw print data) and then prints it Next is to make the dot matrix printer better looking (kinda 3d like on pieter dot com) and have the paper also flowing in 3d out of the printer and integrate it on the page My idea was that it might work because we also capture the COM1 data (from the dial up modem) and send it to a Websocket as a dial up connection, so we should be able to capture the COM2 traffic too but I didn't know how, but now I do IT WORKS!! 😊
0:51

🖨️ It took over a year and lots of help from Claude Code but I have now been able to create a real dot matrix printer on the web that prints from Windows 3.11 in your browser: Here's the test page: I couldn't get the LPT1 port to work but COM2 did work (the dial up model already uses COM1), the JS receives the COM2 serial data (just raw print data) and then prints it Next is to make the dot matrix printer better looking (kinda 3d like on pieter dot com) and have the paper also flowing in 3d out of the printer and integrate it on the page My idea was that it might work because we also capture the COM1 data (from the dial up modem) and send it to a Websocket as a dial up connection, so we should be able to capture the COM2 traffic too but I didn't know how, but now I do IT WORKS!! 😊

@levelsio

85,708 views • 1 month ago

💾 Okay I finally bought a Raspberry Pi 5 to make into a real retro computer as a proof of concept I love the Raspberry Pi much more than my ESP32 simply because I can SSH into it and it's just like a normal computer or server, the ESP32 required specific software to re-flash it everytime and it was TEDIOUS!!!! I need a fast feedback loop to develop with so all this flashing is too slow for me The Raspberry Pi 5 instead just runs Linux which then runs DOSBox-X to run Windows 3.11 install live downloaded from there so it stays fresh I then also got a Checkmate 19" IPS Retro Monitor by Stephen Jones (very indie and Kickstarter-style product) which is like a vintage retro PC monitor but with an OLED and it runs at 1280x1024, and the Raspberry Pi 5 has HDMI out so it works perfectly with it Then I got an 8BitDo retro IBM keyboard, but the spacebar broke, so I gotta send it back and get a new one, but it was great while it worked, so it's not in this video, and I got the 8BitDo retro mouse So altogether it's a proof of concept of a real vintage retro PC with internet and it works now My end goal is to make this into production and SELL it, not for money but more for fun because I think it should exist, just like Palmer Luckey's ModRetro Chromatic Gameboy-remake I'd go with something smaller than this 19" checkmate display though, it's great but too big for the Windows 3.11 era I think, more like 14" with a matching sized retro IBM-style keyboard and Windows 3.11 preinstalled (if legally allowed by Satya Nadella) with WiFi working out of the box We could also go with Windows 98/XP, because for me too Windows 3.11 was a very short time, so I too have vague memories of it, most of my computing memories is Windows 98/XP etc. Inside it could simply run on a Raspberry Pi 5 like here, which is easily powerful enough to run all of these OS'es I see many SF founders with Apple II's in their living room, and I guess cause Apple was more popular there back then, but in the rest of the world we were mostly IBM PCs and clones that ran Windows, so it's cool to have that as one retro object working with internet in your living room Anyway, step by step, we're here now 😊
1:59

💾 Okay I finally bought a Raspberry Pi 5 to make into a real retro computer as a proof of concept I love the Raspberry Pi much more than my ESP32 simply because I can SSH into it and it's just like a normal computer or server, the ESP32 required specific software to re-flash it everytime and it was TEDIOUS!!!! I need a fast feedback loop to develop with so all this flashing is too slow for me The Raspberry Pi 5 instead just runs Linux which then runs DOSBox-X to run Windows 3.11 install live downloaded from there so it stays fresh I then also got a Checkmate 19" IPS Retro Monitor by Stephen Jones (very indie and Kickstarter-style product) which is like a vintage retro PC monitor but with an OLED and it runs at 1280x1024, and the Raspberry Pi 5 has HDMI out so it works perfectly with it Then I got an 8BitDo retro IBM keyboard, but the spacebar broke, so I gotta send it back and get a new one, but it was great while it worked, so it's not in this video, and I got the 8BitDo retro mouse So altogether it's a proof of concept of a real vintage retro PC with internet and it works now My end goal is to make this into production and SELL it, not for money but more for fun because I think it should exist, just like Palmer Luckey's ModRetro Chromatic Gameboy-remake I'd go with something smaller than this 19" checkmate display though, it's great but too big for the Windows 3.11 era I think, more like 14" with a matching sized retro IBM-style keyboard and Windows 3.11 preinstalled (if legally allowed by Satya Nadella) with WiFi working out of the box We could also go with Windows 98/XP, because for me too Windows 3.11 was a very short time, so I too have vague memories of it, most of my computing memories is Windows 98/XP etc. Inside it could simply run on a Raspberry Pi 5 like here, which is easily powerful enough to run all of these OS'es I see many SF founders with Apple II's in their living room, and I guess cause Apple was more popular there back then, but in the rest of the world we were mostly IBM PCs and clones that ran Windows, so it's cool to have that as one retro object working with internet in your living room Anyway, step by step, we're here now 😊

@levelsio

149,119 views • 8 months ago

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.
0:52

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 views • 7 months ago

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

13,396 views • 9 days ago

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.
21:00

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

68,221 views • 23 days ago

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

86,013 views • 6 months ago

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 views • 1 month ago

Someone ran Claude Code on a beach where any device overheats and that spot suddenly turned out to be the best home for the most powerful AI in the world. This is the reMarkable Paper Pro. A paper tablet for notes with no browser and no social media and not a single app. He sat down right on the sand in the open sun and brought up Claude Code on Opus 4.6 over the Claude API on the paper screen and opened his project ~/repos/webs while the waves broke a few steps away. For years every device had the same trouble outside. In direct sun the screen glares and washes out and heats up and instead of your work you see your own reflection. But e-ink does not blast its own light into your face. It reflects the sunlight like the page of a book. And here is what came out of it. The very thing that kills any normal screen outside turned into fuel for this one. The brighter the sun the sharper the picture because it has nothing to glare with and nothing to wash out. And then comes the thing no laptop on a beach will give you. Your eyes do not get tired. You can watch Opus think on max effort for an hour and it reads like a book in the sun and not a backlight you squint into. The picture only comes alive. In bright light it does not fade but turns sharper and higher in contrast than it ever was in a room. The charge lasts for days. E-ink barely touches the battery so there is no outlet anywhere on the sand and the tablet does not care. It weighs as much as a notebook. The whole setup folds into a beach bag like a pad with a pen on top. Everything on the screen is for real. Claude Code v2.1.110 and Opus 4.6 on the Claude API and the project ~/repos/webs open right on the e-ink in the middle of the sand. In my opinion this is the most unexpected home for an AI this year. Not an office with the blinds drawn and not a monitor cranked to full brightness but a quiet sheet of paper on the sand that open sun only makes better and on it the most powerful Claude writes code right on the page like a pen.
0:33

Someone ran Claude Code on a beach where any device overheats and that spot suddenly turned out to be the best home for the most powerful AI in the world. This is the reMarkable Paper Pro. A paper tablet for notes with no browser and no social media and not a single app. He sat down right on the sand in the open sun and brought up Claude Code on Opus 4.6 over the Claude API on the paper screen and opened his project ~/repos/webs while the waves broke a few steps away. For years every device had the same trouble outside. In direct sun the screen glares and washes out and heats up and instead of your work you see your own reflection. But e-ink does not blast its own light into your face. It reflects the sunlight like the page of a book. And here is what came out of it. The very thing that kills any normal screen outside turned into fuel for this one. The brighter the sun the sharper the picture because it has nothing to glare with and nothing to wash out. And then comes the thing no laptop on a beach will give you. Your eyes do not get tired. You can watch Opus think on max effort for an hour and it reads like a book in the sun and not a backlight you squint into. The picture only comes alive. In bright light it does not fade but turns sharper and higher in contrast than it ever was in a room. The charge lasts for days. E-ink barely touches the battery so there is no outlet anywhere on the sand and the tablet does not care. It weighs as much as a notebook. The whole setup folds into a beach bag like a pad with a pen on top. Everything on the screen is for real. Claude Code v2.1.110 and Opus 4.6 on the Claude API and the project ~/repos/webs open right on the e-ink in the middle of the sand. In my opinion this is the most unexpected home for an AI this year. Not an office with the blinds drawn and not a monitor cranked to full brightness but a quiet sheet of paper on the sand that open sun only makes better and on it the most powerful Claude writes code right on the page like a pen.

Blaze

89,297 views • 17 days ago

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!
2:15

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 views • 5 months ago

Richard Donner explains how he managed to include the Anti-Apartheid message in "Lethal Weapon 2" (1989) & why entertainment should always come first- even in message films: "Interviewer: From the process of a chase now to the ideological content, a lot of this movie that anti-apartheid message is loud and clear. What is your philosophy about a message in an entertainment film as opposed to a documentary? Donner: If you want to deliver a message and you're a total believer and you make a message film, you must realize [that] you have a very limited audience. And that's too bad because you have a message to get across. If you you're restricting your audience to that message film you are going to restrict your message you're not going to get it out there. There was a wonderful home made last year called 'A World Apart' (1988) starring Barbara Hershey. It was Chris Menges second film and I thought it was probably the most brilliant direction of the year. I thought [the little girl's] performance certainly deserved acknowledgement by the Academy. Menges's did; the picture did. Nobody saw it [the movie] nobody acknowledged it. It's a sick industry. So, I decided when we had lethal weapon and originally it was written that the heavies were Colombians. I was bored with it and I said, "Jeff let's get something else; let's come up with something a little original." So we [thought] who are the heavies out there? If this was 1942, it would be the Nazis. Where [are] the Nazis [now]. They're in South Africa running the government; so if they're in South Africa let's make them the heavies. On top of it, let's show diplomatic immunity so I can have a Mel Gibson carry an anti-apartheid sign. You can have a diplomatic immunity that's happening in the USA and all the nations that are signatories to it and then you see guys that have committed child m*lest@t!on [and with] diplomatic immunity and they get at home hand slapping sent out of the country. So, we got across a few messages under the guise of entertainment. We got to crush the fact that if you eat tuna, you're ki*ll*ng the dolphins and I get my little and makes me feel good but it's under the guise of entertainment. Interviewer: During all of this, have you defined what best can be done in a Hollywood picture? In other words by combining those priorities? Donner: Yeah, i think so. It makes the filmmaker a little happier for what he's done if he can do something a little more; than just to do an entertainment film with no message whatsoever. Our message in this film is primarily it's a good film; have some laughs, love Mel and Danny. It's good entertainment. You feel good at the end of it and you feel up. That's all I want to do. I'm an entertainer, but if in to within that moment of entertainment if I can sneak one little line in, one little thought, provoke one anxiety in somebody, I'm thrilled." (Richard Donner's interview with John C. Tibbetts, 1989)
2:30

Richard Donner explains how he managed to include the Anti-Apartheid message in "Lethal Weapon 2" (1989) & why entertainment should always come first- even in message films: "Interviewer: From the process of a chase now to the ideological content, a lot of this movie that anti-apartheid message is loud and clear. What is your philosophy about a message in an entertainment film as opposed to a documentary? Donner: If you want to deliver a message and you're a total believer and you make a message film, you must realize [that] you have a very limited audience. And that's too bad because you have a message to get across. If you you're restricting your audience to that message film you are going to restrict your message you're not going to get it out there. There was a wonderful home made last year called 'A World Apart' (1988) starring Barbara Hershey. It was Chris Menges second film and I thought it was probably the most brilliant direction of the year. I thought [the little girl's] performance certainly deserved acknowledgement by the Academy. Menges's did; the picture did. Nobody saw it [the movie] nobody acknowledged it. It's a sick industry. So, I decided when we had lethal weapon and originally it was written that the heavies were Colombians. I was bored with it and I said, "Jeff let's get something else; let's come up with something a little original." So we [thought] who are the heavies out there? If this was 1942, it would be the Nazis. Where [are] the Nazis [now]. They're in South Africa running the government; so if they're in South Africa let's make them the heavies. On top of it, let's show diplomatic immunity so I can have a Mel Gibson carry an anti-apartheid sign. You can have a diplomatic immunity that's happening in the USA and all the nations that are signatories to it and then you see guys that have committed child m*lest@t!on [and with] diplomatic immunity and they get at home hand slapping sent out of the country. So, we got across a few messages under the guise of entertainment. We got to crush the fact that if you eat tuna, you're ki*ll*ng the dolphins and I get my little and makes me feel good but it's under the guise of entertainment. Interviewer: During all of this, have you defined what best can be done in a Hollywood picture? In other words by combining those priorities? Donner: Yeah, i think so. It makes the filmmaker a little happier for what he's done if he can do something a little more; than just to do an entertainment film with no message whatsoever. Our message in this film is primarily it's a good film; have some laughs, love Mel and Danny. It's good entertainment. You feel good at the end of it and you feel up. That's all I want to do. I'm an entertainer, but if in to within that moment of entertainment if I can sneak one little line in, one little thought, provoke one anxiety in somebody, I'm thrilled." (Richard Donner's interview with John C. Tibbetts, 1989)

DepressedBergman

79,994 views • 7 months ago

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.
0:55

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

214,913 views • 1 month ago

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,618 views • 3 months ago