Hacker News: kraakf06https://news.ycombinator.com/user?id=kraakf06Hacker News RSShttps://hnrss.org/hnrss v2.1.1Mon, 15 Jun 2026 14:11:23 +0000<![CDATA[New comment by kraakf06 in "Cybersecurity researchers aren't happy about the guardrails on Anthropic's Fable"]]>False positives like this are probably more damaging than the guardrails themselves. If engineers can't predict when a model will switch behavior, it becomes difficult to trust it in production workflows.

]]>Thu, 11 Jun 2026 01:23:04 +0000https://news.ycombinator.com/item?id=48485134kraakf06https://news.ycombinator.com/item?id=48485134https://news.ycombinator.com/item?id=48485134