Viewing profile — soletta

This reinforces my suspicion that alignment and training in general is closer to being a pedagogical problem than anything else. Given a finite amount of training input, how do we …

Yes, my setup is similar, probably because that’s what Claude drifts towards by default, and in this case I didn’t want to impose my will on it much since it’s a simple problem tha…

I’ve also found that compiling large packages in GCC or similar tends to surface problems with the system’s RAM. Which probably means most typical software is resilient to a bit-fl…

I’ve been doing this for a few months now (rolled my own setup with Claude Code) and it’s totally changed the way I manage my portfolio and retirement plan. I mean yes, this is som…

Interesting. I've been coping by being very conservative about how many rules I introduce into the context, but if what you're saying is true, then something like SCAN actually hel…

I should have been clearer. I'm not talking about making a separate call to the model to ask it to check itself. Any given model essentially is already watching for contradictions …

I was a bit dubious until I read the gist. I've used a similar technique before to 'tame' GPT-3.5 and keep it following instructions and it worked well (though I had to ask the mod…

I watched Claude burn tokens reordering functions in a Rust file, removing each one and rewriting it in the new position, clogging its own context window in the process. I started …

Sounds interesting. What makes DeBERTA + RAG any better than detecting contradictions in the context than a frontier LLM, and why? I see that the NLI scorer itself was evaluated, b…

In the same way we’re making a category error in defining prompt injection, the framing of “AI agents” as primarily “intelligent actors” misses the fact that many of them will be e…

It is by the juice of Zig that binaries acquire speed, the allocators acquire ownership, the ownership becomes a warning. It is by typography alone I can now turbopuffer is written…

The usual path an engineer takes is to take a complex and slow system and reengineer it into something simple, fast, and wrong. But as far as I can tell from the description in the…

Everything I’ve experienced with working with models (from GPT-2 to Opus 4.6) broadly supports the claim that they learn a persona. It comes back to the point that haters love to h…

> if I were an AI and I requested some of those messages (instead of having them injected) into my stream of thought, I would not feel negatively. Good point! I failed to consider …

On the contrary, I think groups that adopt a share-alike approach will, counterintuitively, deepen their moat by increasing the amount of effective world-history-knowledge reflecte…

I’m on board with the sprit of this work and am cautiously acceptant of the claim that it has measurable, positive effects. But have you considered how this would feel if you were …

It’s not reality that’s the moat, though I can see how it’s tempting to frame it that way. And I don’t think the article’s conclusions are that far off. But I think the key is aggr…

A few layout glitches on small screens but otherwise very pleasant! I actually saw an almost identical game, with the same retro vibes, presented at the Roppongi Crossing 2025 exhi…

What the title says. I know AWS has outages but this feels like a stealthy degradation that they aren’t set up to pay attention to. I suppose they think that since any vectors are …