Notes

If elegance emerges from constraints, what happens as the world gets richer?

Sometimes spending more resources is the better solution. Searching every possibility may be easier to understand and maintain than an elaborate way of avoiding the search. The effort saved matters too.

But abundance also makes it easier to live with things we might otherwise have to improve. We can afford the waste. We can work around the complexity. A problem becomes less pressing without becoming any better understood.

I wonder whether that weakens one of the forces that makes our work good. More resources give us more room to experiment, reconsider, and refine. They also give us more room to leave things as they are.

Becoming able to afford a problem can feel a lot like having solved it.

Muse as a free computer

Meta’s Muse gives each user a personal AI agent and a persistent cloud environment. Peter James asked it to export its accessible filesystem, and it obliged.

Jonny Saunders reproduced a filesystem export, then went on to get a root shell and run a torrent client. Meta’s position is that access to the user’s VM files is intended.

Saunders’s broader criticism is about the product: a useful personal agent needs a persistent computer, broad capabilities, and network access. Offer that largely for free, and people can put the computer to purposes of their own:

congratulations: the only form that this kind of product can take is a botnet factory.

Laya

Nandakishor Mukkunnoth is responding to Jev with Laya: an open-weight family of decision models, with Apache 2.0–licensed weights, source code, and benchmark tooling. He points to his own research from March 2025 and writes of TypeSafe AI’s launch:

They proposed the exact same non-autoregressive decision concept as if it was a brand-new scientific breakthrough.

Jev may not be so novel after all.

Introducing Jev

Diogo Almeida, introducing Jev:

While Jev gives up string generation, it’s optimized for structured outputs and can’t hallucinate.

The discussion around Jev has resurfaced how capable older ML approaches remain. For a well-defined task, a fine-tuned BERT classifier can be faster, cheaper, and more accurate than a general-purpose LLM. It can choose the wrong label, but it can’t invent a new one.

But building that specialized solution takes work. LLMs offer useful results across an extraordinary range of tasks without requiring a separate training project for each one. If an LLM already does the job well enough, the specialized alternative has to justify the time and effort needed to build it. That effort is part of what makes a solution better.

I was reminded of the XY problem again today. Once you’ve seen the pattern, it’s surprising how frequently it shows up.

Maybe it persists because offering a solution feels productive, while stopping to articulate the problem feels like delaying progress.

But in a group, articulating the problem is often the higher-leverage contribution. A proposed solution gives everyone something to react to; a clearly stated problem gives everyone room to think.

I’ve wanted to document my stereo system for a while—not just what’s in it, but what I’m listening for and how those priorities shaped it. I finally did.

Few-shot prompting feels strangely unfashionable. Anecdotally, it still works better. Maybe examples aren’t scaffolding on the way to automation. Maybe they’re part of the interface.

It turned out to be easier to explain the personal site I wanted to an LLM than to a framework.

The result is plain HTML and CSS, a little JavaScript, and a Rust program that turns Markdown into the finished site.

Bespoke used to mean more work. Here, it meant less.

I put off rebuilding my personal site because I wasn’t sure what to do with the longer articles I’d written over the years. Some may still be relevant; others, perhaps not.

I wanted a place to capture shorter thoughts. In doing so, I happened upon a pattern I like even better: small notes can live in the feed, while larger ideas can become standalone pages—like my Tides appearance study.

Not every idea needs to fit the same shape.

A light and dark mode study

I built an interactive study while designing a light and dark mode toggle for my site. It let me compare the sun and crescent across sizes and inspect their transition frame by frame. The study became a fun artifact of the process itself.