AI audits of his payment software found bugs that earlier audits missed
Three independent AI audits went through his Cashu payment server and wallet library line by line for a new release. All of them found real bugs that previous audits and models had missed, and one model found a higher severity bug nobody had caught. The release fixes what they found.
How it works
- Three AI models audit the code line by line
- Each finds real bugs earlier audits missed
- He fixes the findings and ships the release
Why it’s worth knowing
Every model found bugs the others and all previous audits had missed, including one higher severity bug found by a single model.
Where it’s from
Summarized from a public post on njump.me. See the original ↗