Viewing profile — strujillo

Yeah exactly — that “no LLM in the loop” constraint forces everything to be explicit and verifiable. I put together a few experiments where the system rediscovers known laws direct…

Exactly — that was the surprising part for me too. The system has no notion of “physics” at all — it’s just searching for compressible structure in the data. The fact that GR relat…

Thanks! The key insight: don't fight the model's limitations, design around them. Our agents never touch retrieval or search — that's all deterministic code (FTS, sparse regression…

ProtoScience is a deterministic pipeline that takes raw numerical data and autonomously discovers governing equations. It does not use LLMs for discovery — only sparse regression, …

That matches what I’ve seen as well — generation is the easy part, validation is the bottleneck. I’ve been experimenting with a small sparse-regression system that infers governing…

Sparse workloads are a really good fit for scientific discovery pipelines, especially when you're searching over candidate equation spaces. In practice, even relatively small syste…

It’s impressive how mature Pyodide has become — running Python scientific tools in the browser opens up a lot of possibilities. I’ve been working on a small (~800-line) Python syst…

Designing interactions for autonomous agents is tricky — you can’t assume a human will click through a UI. I’ve been experimenting with autonomous scientific agents: a lightweight …

Formal verification and code synthesis feel like natural companions for automated scientific discovery. I’ve been working on a small (~800‑line) Python agent that uses sparse regre…

[dead]