I’ve moved my agent skills from a GitHub repo to my Obsidian vault. Git has felt too heavy for working with some simple Markdown files and Python scripts, and it’s so nice to have them auto synced across devices.

Treating myself to a hit of the ✨ new tools ✨ drug during my work break. So far: Claude Code → OpenCode + OpenChamber Notion → Obsidian Cursor → Zed

The last time I tried @zed.dev (like a year ago) I think wasn’t happy with the polish on some of the AI features. Now that I’m using separate apps for AI, I just want a fast and good text editor. Maybe it’s time to give it another try.

Yeah, this just changed my view. Starting from scratch risks building the wrong thing, whereas other companies can be a good proxy for what you want to do. simonwillison.net/2026/May/6/v...

this to me is what makes human intelligence so useful/valuable

The Last Software Engineer www.epicproduct.engineer/the-last-sof...

I’m interested in “is AI+(Human expert)>AI>HE” for that half. Ie in which areas are we relevant as team members and how.

Can I already watch @danabra.mov’s talk from #atmosphereconf anywhere?

I really want to make a thing that you can point to a random poorly documented API and figure it out by trial and error. Then write the docs and self-evaluate ability to use the API with docs; repeat. Needs a good resettable sandbox env but would make APIs much more usable for AIs and humans.

With all these tracking apps on atproto I think the time might be ripe for an aggregator “tracker of trackers”. See what you can learn when combining all that data. And the open data protocol makes it possible.

Apparently Google is blocking Gemini requests from Claude Code on web. So I guess I either have to switch to Jules, or switch my Gemini requests to Claude. It's pretty clear which has the bigger moat though 😅

Booked tickets for AIE World’s Fair in SF this summer. See you all there 😎

Back on that virtual try-on shit ✨

This looks cool! I’ll be there 🌊

Interesting to see that Rust is still harder for LLMs than other languages, and this matters on hard tasks! It’s not automatically the best choice when you need something fast and reliable.

I don’t have a deep understanding of what Next.js does, but the message of “we reimplemented the entire API surface of this heavily iterated 10 y/o project and made it 4x faster in one week” is just absolutely wild

From subjective experience, Sonnet now feels just as slow as Opus. Maybe not in raw tokens, but in outcomes. I’d love to see model labs start measuring this more.

I'm afraid I'm going to be reposting this every day until the far side of the singularity. Work on the things you want to see more of! Work on flourishing! Work on things that are freeing!

This is so true and I'm happy it turned out this way. Humans + AI both benefit. The reason why it's MORE important now is that LLMs forget everything while humans learn from trial and error. We need to compress all that learning into documentation.

This is so awesome. The fact that I can turn my expert coding agent into a really good teacher by dropping some files in a folder is just wild.

Ooh, I like this direction. I’ve been experimenting with keeping thinking disabled for straightforward tasks, mainly for speed.

I really wish model labs would start posting benchmarks on speed and token efficiency. Can’t we just measure the time/tokens to complete existing benchmarks? Especially interested to see if smarter models can be faster on certain tasks by needing fewer tool calls.

Let’s make some virtuous software today

stranger: what do you do for work? me, shamefully: computer

For all you digital gifters, I made a heart-shaped QR code generator 💝 Can also be used for links or secret love notes! 🤫💕 (only tested scanning on iphone) qheart.vercel.app

For all you digital gifters, I made a heart-shaped QR code generator 💝 Can also be used for links or secret love notes! 🤫💕 (only tested scanning on iphone) qheart.vercel.app

always so funny to me when people are like “how am I supposed to explain Gay to my kids?” my kid asks me way harder shit all the time. “why did they build the road this way? why are some people bad?” I don’t know. please ask me about Gay

Sitting in a cafe telling the computer what to do all day is a new level of work in public

I’ve been getting so many chores done while Claude is working 🧽

Agentic coding is starting to feel cost-bound again for me. I use API-based billing (bc work) and I’m no longer sure that what I build is necessarily worth the price tag. $20 for a feature is not much, but also not negligible. And I don’t like that I have to consider that before starting.

I think CLIs are winning precisely because they are *not* very open-ended. You’re fully constraining yourself to text input/output, and that’s great for LLMs.

Made a self-updating skill for scaffolding React projects. It runs a script so I get a fast and consistent setup every time, but uses the LLM to update the script based on shadcn docs. github.com/nimobeeren/s...

I've been having way more (good) interactions on here for the last few weeks! I was added to a starter pack but I feel like it can't just be that. Probably For You has something to do with it? 💖

Trying to explain nondeterminism in LLMs: it's like talking to clones of the same person but they're in a slightly different mood each conversation

Rambling into a recording device like it’s the 70s, except I’m not causing psychic damage to the person who is asked to transcribe it

The whole “prompt engineering” thing still has people believing you need to speak some arcane language to make good use of LLMs. In reality, you just need to be unambiguous, structured and complete. No tricks necessary.

Sonnet is definitely due for an upgrade! Opus is actually faster for me in most cases because it calls the right tools instead of messing around.

Yeah, like please invest that effort into turning your app state into local Markdown and JSON (or SQLite) files so I can use my good AI tools to work with it

The other big win with agents is that they let people do things that were completely out of reach for them before. So, not a productivity win, but a capabilities win.

While Claude is definitely useful for boring, large scale refactors, it’s most fun when it lets you do something you just couldn’t do before. For me that’s complex algorithmic optimization.

Moltbot is a pretty strong signal to me that software security is going to get a lot worse before it gets better. We're in for a wild ride.

I wish models didn't leave code comments like this. It only serves to highlight the current change, but has no value to readers of the code in the future. Haven't been able to prompt this out yet.

I'm blasting some ~lofi~ and having a beer, gotta maximize those vibes while Claude codes ✨

The default behavior when sending a new message in an AI chat app should be to scroll new message to the top and then STAY THERE. I don’t actually want my text to auto scroll and be unreadable until streaming stops. Sucks that this is hard to implement though!

Apparently it's still really hard to make a scroll container stick to the bottom while content is being added (i.e. every AI chat app ever). Have there been any developments to make this easier in web apps?

Subagents just landed in Cursor 2.4! I think these will be especially useful for tasks at scale, e.g. create 100 components/pages/test suites in parallel. They also ship some subagents which run automatically. This looks like a nice optimization to avoid context bloat.

Today’s models feel very strongly biased towards keeping existing code instead of rewriting. Almost like the sort of laziness from GPT-3.5 times. I think I need to work on my tests and make a habit of deleting large parts of implementation.

Even if LLMs can’t write “production-ready” code to your standards (and you are sure those standards are still serving you), they let you iterate and explore so much faster. Even the best programmer doesn’t always know what users want. Prototypes help you get that feedback.

Is there a future where TypeScript types could ever be read at runtime? It’s the one thing I miss coming back from Python