Ask HN: What Are You Working On? (Nov 2025)

Working on AI interpretability infrastructure! Starting with hallucination/failure mode detection and causal tracing in transformer-based foundation models. It's non-SAE, domain-agnostic, and works for any kind of tokens or sequence data (e.g. not just English text - biological sequences, physics data, etc). Some of our early tests indicate that this detection setup could broadly work well for any property, but we've mostly validated on hallucinations. If you have access to self-trained or open-weight models, would love to have you try out the alpha version - running it through HuggingFace!

Figuring out the semi-documented method of doing varargs on the Mac AArch64.

I am currently working in a big Italian company that makes 90% of the glasses, and recently it’s collaborating with Meta to make smart glasses!

Reviving a dead PHP bytecode vm for embedded systems:

https://github.com/alganet/PHL

---

Bootstrapping from an x86 image that is mostly source text (based on live-bootstrap):

https://github.com/alganet/abuild

---

Image with many shells, for testing script for portability:

https://github.com/alganet/shell-versions

a bloomberg terminal for prediction markets