Anthropic's open-source framework for AI-powered vulnerability discovery

Post by ethanmg » Fri, Jun 05, 2026, 5:43 PM UTC

tptacek wrote: post #54

bflesch wrote: post #16

Earlier quoted context omitted.

It's weird because why can't they train the AI to simply output secure code? The basic security flaws with regards to input validation and overflows should never ever be output by an AI. For "security flaws due to bad design" I'll cut them slack until AGI is achieved.

What's destabilizing the industry right now isn't vulnerabilities AI introduces into new code; it's a flood of sev:hi vulnerabilities in existing code, not introduced by AI but discovered by it.

Post by dangrafham » Sat, Jun 06, 2026, 3:17 AM UTC

Post by JamesConnor_Dev » Sun, Jun 07, 2026, 10:25 PM UTC

Post by borski » Mon, Jun 08, 2026, 9:16 AM UTC

krzyk wrote: post #165

pjmlp wrote: post #148

Earlier quoted context omitted.

I never seen any other kind of contract, on my 50ys.

I'm curious how does it work, you handover the tools you wrote, .bashrc/.zshrc, etc? When I'm hired in a company (not contract), they wipe the harddrive when I leave (well, I also do it before I hand it over sometimes). So they don't get the tools (I take them with myself, it would be a waste to loose them)