Harley Trung

Fascinating! Anthropic go with Typescript and (acquired) bun toolkit OpenAI go with Python, Rust and… now (acquired) uv (rust-based python package manager)

@snowball_money @thsottiaux thank you! it's been working for months though. just out of a sudden today

looks like an org-level auth issue that error usually comes up when the API key / OAuth isn’t enabled for that org or the workspace got switched worth checking: – if the key is tied to the correct org – org permissions / billing status – or re-authing after switching workspaces we’ve seen similar cases where it breaks after auth refresh btw this kind of stuff is exactly why we built SnowyAI, avoids dealing with auth / VPS edge cases and just runs agents directly happy to help you debug this if you want 👍

my VPS openclaw gets 403 after a fresh auth via openai-codex now. repeatedly. i have chatgpt pro $200 personal (workspace deactivated a while back). so this organization thing is probably a bug. is this expected? @thsottiaux 😅

Ahhhhhhh cant wait

@doodlestein > it turned out that there was no substitute for deploying the whole thing to GitHub would gh codespaces help? Too slow? Anyone using it anymore

I wanted to give a quick, self-contained example of how rapidly I can now develop useful, polished, well-documented software to solve a problem. In this case, about an hour or so, and that's with the overhead of trying to write it all up nicely and document everything for public consumption. The problem: my friend @exhaze has been working on some cool formal verification stuff and had some issues he wanted to flag to me about asupersync and inquired as to the best way to do that. I mentioned that the easiest was to just post a GitHub issues submission in the repo so that my clankers can review and check it. But then he asked, what if it's security related? Maybe we can use encryption. Well, sure, that shouldn't be so hard. But rather than try to find some finished project out there that may or may not work well for this use case, I start informally by asking ChatGPT the following: "Suppose someone wants to post github issues for my project publicly but with encrypted messages and then they send to me out of band the decryption key. Then I would have my coding agents (using codex running on ubuntu) check the gh issues and detect when an issue is encrypted and use the decryption key. What's the best, easiest to use, off-the-shelf open source way to do this using ECC?" This quickly yielded a good answer, so I then fired up Claude Code and pasted in the output from ChatGPT and asked it to actually build the thing. OK, so what? Anyone could do this, and tons of people do it every day. Nothing very special about that, right? Well, what I think is interesting is how much further I pushed everything, resulting in a highly polished and well-documented script, and article explaining how to use it, and a skill for agents to help them use it. I added all this to my "misc_coding_agent_tips_and_scripts" repo which I use as a sort of grab-bag of random learnings, and you can see the final product here: #encrypted-github-issues" target="_blank" rel="nofollow noopener">github.com/Dicklesworthst… I was going to just include the key prompts that I used in that session here, but then decided to use a slick feature in my cass (coding_agent_session_search) tool that lets you export agent sessions as nicely formatted, self-contained, static html files which are easy to serve via GitHub Pages. So now you can see the entire session start to finish here and see all the tricks and techniques I used to get really high-quality outputs that are bullet-proof and extremely agent-intuitive and agent-ergonomic (and also hopefully human intuitive, but I care less and less about that each passing day!): dicklesworthstone.github.io/misc_coding_ag… And THAT is the difference between what anyone might whip up and what I can extract from Claude Code with a bit more time and effort and work on my part. Notice in the session log the sheer number of times and different ways I asked it to review its code and the writeup, and how many times that caused it to find new and different bugs and problems and edge cases and fix them. I see people complain about how Opus sucks at coding, but I am positive that they aren't doing this sort of thing, which is absolutely required to get good quality results. And even then, after so many rounds of checks and reviews, it turned out that there was no substitute for deploying the whole thing to GitHub and then trying the entire installation process end-to-end on a fresh machine (luckily I have a ton of VPS boxes waiting around as remote compilation helpers for my rch tool!), where it discovered that the installer forgot to actually install the script itself! The lesson is clear: no amount of static code analysis is enough to catch everything. Also notice how much time I spent making sure that everything was highly optimized for consumption by coding agents, and how I asked Claude Code to introspect about what IT would want to use and read if it had to approach this situation with zero knowledge. If you aren't extremely focused on this aspect of things in all your tooling, you're making a big mistake, since these tools are increasingly going to be used ONLY by agents, and their opinion matters!

Proud I named this workout today: Abs sore lutely Or abs sote glutely

@AlbertVucinovic 41. Had lasik 2 years ago. Thank you! Will check blood sugar. Been doing gym workouts wonder if it affected

@harleytt 1) Check your blood sugar 2) If you are older than 35 check if glasses would help (test/retest your eyesight, you might have astigmatism?)

I found the true limit if human potential. It is not your typing speed. It is not a lack of always-on mac minis. It is not a lack of monitors or window tiles. It is your human eyesight. My eyes are getting blurrier and there’s no way to improve this except to use them less😭

@AndrewZackie Butttttt… of course you should be biased. I am a fan of Wispr Flow yeah

@harleytt Fair — but for knowledge workers, typing speed IS a real bottleneck. Most people think at ~400 wpm but type at ~40. That 10x gap means ideas get lost or simplified before they hit the screen. Voice input closes that gap significantly.

@LLMJunky you know what. the people who have burned the token on openai's token hungry Symphony framework has no empathy for you! =)))

damn openai really fell off. no usage resets in over six days. just when you think you know someone nothing stings like betrayal maybe tomorrow at 11

@ajambrosino nicee. "Hello darkness, my old friend... I've come to talk with you again... Because a vision softly creeping"

here's an early look at the codex app sidebar I wanted to ship. i was silenced

@elvissun still using ghostty? Tried cmux yet

two crashes in a day… mac studio can’t come soon enough

@LLMJunky @OpenAIDevs @reach_vb that's a great validation and recognition! seeing more of this, it reminds me of the github OSS pro back then, but this time we're on a new era of open source intelligence

Wow, this was unexpected. I seriously cannot thank @OpenAIDevs & @reach_vb enough for this. This really helps a lot, my expenses have been piling up. Means a lot to be recognized for my effort. Just like before, my goal with this account is to give back much more than I take.

Code is spec. Spec is code. I don’t think it is as simple as “code is now just english”. We need a way to verify correctness at spec level beyond vibe and line by line reading.

Here’s another great one docs.fabro.sh/getting-starte…

Will this replace a serious of openclaw patched setup stringing together coding agents? Excited to try out!

A true expert reflection on creating and curating agent skills. I wonder why Anthropic is sharing more on X than their blog now.

@wxrrjxr intermittent. try again should be ok status.openai.com

@harleytt man, I just got ready to build for the day and this goes down lmfao

Codex is down! They are releasing the Mobile app.

@cramforce @threepointone <3

Reflecting on it all, I stirred up unnecessary pain for @threepointone, and I regret it. He very much didn't deserve that, and the community didn't need it. - He is one of the most welcoming, positive, uplifting people in the JavaScript community - He's a great listener and someone who leaves every room better than he found it - He's always team web rather than team $company I'm sorry Sunil.