If that type of scanning works and discovers these attacks, why not make it part of the publishing process?

Using LLM to target an FPGA would be interesting, generate the Verilog/VHDL.

much faster, above all, but this would be electronic signal processing with quantisation etc. I am targeting zero latency purely analog circuit. I'm not sure if FPGA can do it...

is there a link to the project, the one in the comments won't open on mobile

If it helps I've been doing a lot of projects with TSX (via OCX) as a file format.

It works nicely for these things because it already supports typed parameters and can be treated as a a raw AST without JS engine.

Its also easy to manipulate with the same library.

Yeah, a typed tree structure is definitely what we want here.

I guess you mean https://github.com/oxc-project ?

Are there benefits compared to using, say, protobuf?

Because one is for lawyers? It doesn't seem like a hard choice.

Same here. Then you see SOTA in a browser from Ex0byt, online 10x training (JIT-Lora), TurboQuant (Google), etc. Just saw KV prediction mentioned in this thread, so looking into that too.

I'm adapting all of this to Rust+WGPU with compute shaders if you want to follow along.

See this repo: https://github.com/tmzt/shady-thinker

Goal is Qwen3.5 27b on a Pixel 10 Pro running GrapheneOS.

Gemini Nano is supposedly doing it on device. It looks like something similar should work with Apple GPU and ANE.

Or a grinder and a camera. See CCC of years past.

What is the API key used for?

My guess is that Nia Vault uses Nia.

> Nia is an API and MCP layer that gives agents continuously updated context from libraries, research papers, and docs, so they don't hallucinate and you skip manual ingestion.

s/PROGMAN/EXPLORER/g