Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Show HN: ACE – A dynamic benchmark measuring the cost to break AI agents (fabraix.com)
9 points by zachdotai 10 days ago | past | 3 comments
We've had more AI security incidents in 2026 than all of 2024 (fabraix.com)
4 points by zachdotai 14 days ago | past
SWE-bench will hit 90% this year (fabraix.com)
6 points by asfsf23423 17 days ago | past | 4 comments
SWE-bench will hit 90% this year (fabraix.com)
2 points by zachdotai 22 days ago | past
Weekly "Wordle" for Breaking AI Agents (fabraix.com)
1 point by zachdotai 42 days ago | past
Weekly "Wordle" for Breaking AI Agents (fabraix.com)
2 points by zachdotai 63 days ago | past | 1 comment
Show HN: Fabraix Playground – Weekly Wordle for Breaking AI Agents (fabraix.com)
5 points by zachdotai 64 days ago | past | 1 comment

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: