{"slug": "show-hn-beating-gpt5-5-xhigh-for-coding-agent-security-with-slms-and-irm", "title": "Show HN: Beating GPT5.5-xhigh for Coding agent security with SLMs and IRM", "summary": "A cybersecurity startup claims its small language model, post-trained with inline reference monitoring, outperforms GPT5.5-xhigh on coding agent security benchmarks including LinuxArena and SleightBench. The free product is available at harden.run, with full benchmarks in the blog post.", "body_md": "Coding agents craft arbitrary code so securing them is more complicated than red-teaming. We post trained a cyber-security small llm, changed how it reasons and supplemented our controls using program analysis techniques such as inline reference monitoring to outperform GPT5.5-xhigh on hard benchmarks like LinuxArena and SleightBench.\n\nFree product available at harden.run and full benchmarks in the blog post.\n\nComments URL: [https://news.ycombinator.com/item?id=49472151](https://news.ycombinator.com/item?id=49472151)\n\nPoints: 2\n\n# Comments: 1", "url": "https://wpnews.pro/news/show-hn-beating-gpt5-5-xhigh-for-coding-agent-security-with-slms-and-irm", "canonical_source": "https://harden.run/blog/aif-research-and-evidence", "published_at": "2026-08-27 22:33:19+00:00", "updated_at": "2026-08-27 22:48:03.087168+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-research", "ai-products"], "entities": ["GPT5.5-xhigh", "LinuxArena", "SleightBench", "harden.run"], "alternates": {"html": "https://wpnews.pro/news/show-hn-beating-gpt5-5-xhigh-for-coding-agent-security-with-slms-and-irm", "markdown": "https://wpnews.pro/news/show-hn-beating-gpt5-5-xhigh-for-coding-agent-security-with-slms-and-irm.md", "text": "https://wpnews.pro/news/show-hn-beating-gpt5-5-xhigh-for-coding-agent-security-with-slms-and-irm.txt", "jsonld": "https://wpnews.pro/news/show-hn-beating-gpt5-5-xhigh-for-coding-agent-security-with-slms-and-irm.jsonld"}}