Animated multi-agent bug-hunting flow with Opus 5.5 as verifier
The author animated a workflow where one AI flags bugs, Opus 5.5 checks them, and a human makes the final call.
1 person. A day job. Anthropic's AI hunting bugs for 31 days. It found 171. 4 out of 5 got thrown out. The win came from the setup, not a smarter model: > AI #1 hunts. Its only job is to find suspects > AI #2 tries to kill each suspect. Only survivors move up > another model checks again, so one model's blind spots don't pass > a human makes the final call. In the paper, AI found 0 bugs fully alone Result: about 135 suspects dead. 4 became official security bugs (CVEs). Same idea, another study (Monash University): just asking AI "is this bug real?" caught 36.4% of fake alarms. an AI agent that checks the code caught 95.5%. I animated my version: Jev flags, Opus 5.5 checks, my spider pulls only what survives. Try it today: when AI finds a bug, open a new chat and ask it to prove the bug is fake. Finding bugs is cheap. Proving them is the job. Your AI found bugs today? Until something tries to kill them, they are guesses.
This post quotes another post: x.com/noisyb0y1/status/2105964235087856080