New https://t.co/7xgRvduBth is live 😱
Request an audit in a few clicks, and browse 170+ security reviews filtered by chain, language and status.
https://t.co/8Lk1EsKFcj 🫡🫡
Another Robinhood Chain protocol audited ✅
@DarkWalletRH came out of our review with informational findings only. Clean code, solid design, and a team that clearly takes security seriously.
Read the full report 👇
https://t.co/PWANf5VqYT
@realmtbman I’d build a next-generation autonomous AI model for CT and MRI analysis, aiming for 90%+ accuracy in detecting abnormalities, identifying pathologies, and generating detailed radiology reports.
I stopped asking AI to find bugs. I've built an AI workflow that runs semi-automatically and consistently finds Critical issues.
I used this system alone in the @immunefi audit competition for @QuantusNetwork. It found a Critical issue nobody else did, and I finished 2nd out of 98 researchers.
Then, with two days left in the @Firelightfi Audit Competition, I ran it and found a paid High.
Same for the ENS Audit Comp. I launched it in the last two days and found me a Critical.
Honestly, I’m very proud of this AI workflow I've built. And I'm still improving it to work for Bug Bounties even more autonomously.
I already knew the system worked because it constantly finds issues in private client repos. But seeing it work in a public contest, with everyone looking at the same code, is different.
And yes, I genuinely need to start doing bug bounties.
I wrote an article explaining exactly how I did it, which models I used, what worked, and also what failed.
Btw, screenshot with proof below.
@markfenner > I want to build an autonomous AI agent for CT and MRI analysis, aiming for 90%+ accuracy, to help radiologists detect abnormalities faster and make more confident decisions. Not to replace doctors, but to give them a powerful second pair of eyes.
@cyrilXBT Fake. Boris Cherny debunked this himself: "I did not write this.. please don't attribute stuff to me if it wasn't me." Dead giveaway on page 1: the logo says "ANTHROP\C" — a mangled AI-generated wordmark. No such document exists on his X, GitHub, or Anthropic's site.