https://hackerpaper.kaipfister.de/p/2608.23873/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMThttps://news.ycombinator.com/item?id=49525220urn:hackerpapers:submission:2608.23873:49525220Tue, 01 Sep 2026 17:40:13 GMT<p>Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo)</p><p>I&#x27;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&#x27;m excited for you to play with the tech — see if YOU can break it! (let me know if you can) Paper at…</p><p>6 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2608.23873/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI