Bitcoin Core is some of the most reviewed code in the world.

We were curious how our frontier AI model would handle it. Last month we ran 16 agents across 5 of the top models for a week to look for issues in Bitcoin Core v32.0rc1

Impressively, they surfaced two minor items - both now disclosed responsibly.

Agentic teams have been a huge unlock so far for our security efficiency. They're also remarkable to watch.

Credits: https://twitterviewer.app/JLunglhofer/status/2115791872077541408

My notes, check the image: the analisis is impressive 😮, they have access to models not available to the general public. Only a few selected organizations can access Claude Mythos that is currently the top frontier model regarding security analysis (it is not available to the public because of its outstanding availability to write exploits and find security issues).

i.redd.it