Hacker News: totallyrandom__https://news.ycombinator.com/user?id=totallyrandom__Hacker News RSShttps://hnrss.org/hnrss v2.1.1Fri, 08 May 2026 16:44:44 +0000<![CDATA[New comment by totallyrandom__ in "Dirtyfrag: Universal Linux LPE"]]>Am I missing something? Where does it say that the researcher that found Dirty Frag used LLM to find it? Have you read the original report from the researcher?

]]>Fri, 08 May 2026 14:58:07 +0000https://news.ycombinator.com/item?id=48064159totallyrandom__https://news.ycombinator.com/item?id=48064159https://news.ycombinator.com/item?id=48064159<![CDATA[New comment by totallyrandom__ in "Dirtyfrag: Universal Linux LPE"]]>Where does it say that the Dirty Frag one was found by LLMs? The research site with all the information doesn't mention LLM or AI at all.

]]>Fri, 08 May 2026 14:56:53 +0000https://news.ycombinator.com/item?id=48064140totallyrandom__https://news.ycombinator.com/item?id=48064140https://news.ycombinator.com/item?id=48064140<![CDATA[New comment by totallyrandom__ in "Mozilla Used Anthropic's Mythos to Find and Fix 271 Bugs in Firefox"]]>Anthropic said they used 1000 agents worth $20k of token to discover "several dozens" of vulnerabilities in OpenBSD, of which only one was cool enough to mention it and brag about. That's not including the cost of 196 reviewers they also used.

The question is, if Firefox was given $20k worth of credit to find these vulnerabilities, how many vulnerabilities could have been discovered by paying that much money to security researchers who wouldn't have needed additional reviewers?

]]>Thu, 23 Apr 2026 04:29:16 +0000https://news.ycombinator.com/item?id=47872250totallyrandom__https://news.ycombinator.com/item?id=47872250https://news.ycombinator.com/item?id=47872250