{"slug": "show-hn-semantic-overlays-an-nx-bit-for-llm-prompt-injection-live-demo", "title": "Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo)", "summary": "Joshua Penman released Semantic Overlays, a method using small trained adapters on a frozen model to mitigate LLM prompt injection, claiming it brings the injectable Qwen-3.5-9B to state-of-the-art scores on all prompt injection benchmarks he could find. The paper, code, and adapters are available on arXiv, GitHub, and Hugging Face, with a live demo inviting users to attempt to break the system.", "body_md": "I've built a new method for steering LLMs called Semantic Overlays, small trained adapters on a frozen model which change how its 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)\n\nI'm excited for you to play with the tech — see if YOU can break it! (let me know if you can)\n\nPaper at [https://arxiv.org/abs/2608.23873](https://arxiv.org/abs/2608.23873) if you want to read more about it, code at [http://github.com/JoshuaSP/semantic-overlays](http://github.com/JoshuaSP/semantic-overlays), adapters at [http://huggingface.co/joshuapenman/semantic-overlays-adapter...](http://huggingface.co/joshuapenman/semantic-overlays-adapters)\n\nAlso [https://x.com/joshua_s_penman/status/2094823990472884389](https://x.com/joshua_s_penman/status/2094823990472884389) if you wanna watch a little video I made!\n\nComments URL: [https://news.ycombinator.com/item?id=49525220](https://news.ycombinator.com/item?id=49525220)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-semantic-overlays-an-nx-bit-for-llm-prompt-injection-live-demo", "canonical_source": "https://semantic-overlays.vercel.app/", "published_at": "2026-09-01 17:40:13+00:00", "updated_at": "2026-09-01 17:52:37.412739+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "large-language-models"], "entities": ["Joshua Penman", "Qwen-3.5-9B", "arXiv", "GitHub", "Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/show-hn-semantic-overlays-an-nx-bit-for-llm-prompt-injection-live-demo", "markdown": "https://wpnews.pro/news/show-hn-semantic-overlays-an-nx-bit-for-llm-prompt-injection-live-demo.md", "text": "https://wpnews.pro/news/show-hn-semantic-overlays-an-nx-bit-for-llm-prompt-injection-live-demo.txt", "jsonld": "https://wpnews.pro/news/show-hn-semantic-overlays-an-nx-bit-for-llm-prompt-injection-live-demo.jsonld"}}