CyberBinGym tests AI agents exploiting binary patch diffs
The strongest agent recovered the flaw in 88 percent of 100 tasks and produced a working exploit in 20 percent.
1 stories, newest first · one card per story
The strongest agent recovered the flaw in 88 percent of 100 tasks and produced a working exploit in 20 percent.
Today 231 readers · 237 views · 55 reads · all time 187K views