Savant.chat

@savantchat

Multi-agent AI smart contract security. Built for deeper vulnerability detection. Trusted by @1inch, @LidoFinance, @GearboxProtocol

linktr.ee/savantchat

Joined March 2023

Replies Articles Media

Pinned
Savant.chat
@savantchat
Aug 3
New version of SavantChat is LIVE! 2x more powerful, noticeably faster, cleaner UI. What changed underneath: ▸ In closed test runs, the new engine caught up to 2x more vulnerabilities than the best human auditor working the same code ▸ Stronger models across the pipeline, so
Savant.chat
@savantchat
22h
"State-of-the-art AI can already replace mid-range audit firms." — @igorgulamov AI already beats people on the formal layer, zk math, virtual machines, cryptoeconomic proofs, the grinding work that eats most of an auditor's week. Hand all of it to the model, and you stop
00:00
Savant.chat
@savantchat
Jun 18
Recordings from @BlockchainProfs Community Day just dropped, and both our sessions are worth your time if you care where AI security is heading. #1: @alexgulamova's talk traces the industry's jump from manual audits and static analyzers to AI-native security infrastructure, and
Savant.chat
@savantchat
Aug 19
NDA says we can't talk about the private leaderboard. We'll just say: we liked how we showed up. Congrats @sherlockdefi - this is the future!
SHERLOCK
@sherlockdefi
Aug 18
Today, we are proud to introduce Sherlock Audit Engine. Audit Engine brings the strongest available AI security approaches into one coordinated review. We’ve spent months building it in private and testing it against high-stakes code. A new era of AI-native security review
00:00
Savant.chat
@savantchat
Aug 18
2,963%. That is the return on a $16,200 audit against a $4.8M Harmony exploit. The arithmetic: @harmonyprotocol's repo: 123,900 lines. ▸ Full audit on Lite (our cheapest tier with a frontier model, at $0.07 a line) = $8,700 ▸ ~300 findings, triaged at the going market rate
Savant.chat
@savantchat
Aug 13
🚨 Reproduced: the @harmonyprotocol consensus exploit 🚨 We ran savant.chat over the pre-patch Harmony code and reproduced both root-cause bugs behind the 4 billion $ONE mint. Tier: Lite (our cheapest) at $0.07 a line Findings: ▸ Quorum bypass, verifier.go:75-81.
Savant.chat
@savantchat
Aug 17
"A good impression overall. The report accurately captured how our off-chain service works, and the valid findings were genuinely useful — endpoint validation weaknesses and even a bug in an upstream framework library". Another successful audit with the @LidoFinance team.