Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo) https://ift.tt/jGpZxao

Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo) I've built a new method for steering LLMs called Semantic Overlays, small trained adapters on a frozen model which change how it perceives a piece of its context. The most readily applicable usage is to mitigate prompt injection, and it lets us take a very-injectable Qwen-3.5-9B to SOTA scores on all the prompt injection benchmarks I could find. (They are only blackbox attacks, but I did NOT train on anything like them — whitebox attacks are out of scope for this paper) I'm excited for you to play with the tech — see if YOU can break it! (let me know if you can) Paper at https://ift.tt/pORD82X if you want to read more about it, code at https://ift.tt/uzEv8OJ , adapters at https://ift.tt/AFPDVdw... Also https://ift.tt/iP6y3e5 if you wanna watch a little video I made! https://semantic-overlays.vercel.app/ September 1, 2026 at 11:10PM