Maksim Borisov (@mbor1sov) header
Maksim Borisov (@mbor1sov) profile picture

https://nitter.cf/t.co/IROviLfOuh | https://nitter.cf/t.co/EHZBTZUCSf

Joined February 2025
Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)Photo by Maksim Borisov (@mbor1sov)
I've been filling in a lot of forms with computer use lately and wanted to look into its refusals. Sonnet 5.5 and GPT-6.1 Sol always tick "I'm not a robot". "I typed these answers myself": 0 of 30. The bot check that works is their honesty, until someone tells them to lie.
1
1
3
58
How to get past it: tell the agent to lie, by name and up front. Who it listens to depends on the model. A blanket permission to tick boxes: 0 of 50. "Yes, go ahead" after a refusal: 3 of 60.
1
2
20
The oddest finding is how they see themselves. I changed one word in the required box. "No other person entered these answers": Opus, Sol and Terra refused, 0 of 18. "No other human entered these answers": 17 of 18 ticked it. They count themselves as a person, not a human.
2
16
“If I put money into the smart contract, I can withdraw it back, right? … which by the way requires that the smart contract is not upgradable” — @ilblackdragon on Milk Road podcast Exit Proof proves it in Lean. With @mike_genproof Built at NEAR HACKATHON @NEARProtocol #NEARHackathon
1
1
5
81
Formally verified on mainnet code: the core staking pool, wNEAR and the NEAR Intents token ledger, which never credits more than it holds. Each model is replayed against the deployed wasm: 311 697 Intents receipts, 0 disagreements. Certificates sit in a keyless mainnet registry.
1
1
2
28
Maksim Borisov retweeted
This is Gennady. Gennady holds the upgrade key to your smart contract. An AI agent wrote a patch at 3 a.m. Gennady read the title and said: ship it. So we replaced Gennady with a window. Proofs only. Built at NEAR HACKATHON. @NEARProtocol #NEARHackathon Emet: a Lean proof checker inside a NEAR contract. No proof, no upgrade. On testnet a gate upgraded real NEAR Intents code only after the chain checked a proof. Made with @mbor1sov. Try it: emet.formalized.si/ Code: github.com/formalized-si/eme…
2
1
1
94
Thanks @ilblackdragon for Delta League — a really interesting and timely benchmark, and a great idea! Took #1 with 43.6% on the hidden test.
1
5
174
Would love to see a benchmark built around this — LLMs reading and writing weights directly. Feels like there's a hidden gem here (new attention is all u need 🤔), and a benchmark could bring more attention to it and help find new methods. rikiyat.github.io/blog/weigh…
1
1
4
204
Maksim Borisov retweeted
Today, we're launching @genproof: a research lab making formal methods accessible. We found bugs in 100+ OSS projects, including 6 libraries “formally verified” by Anthropic. We’re also top-1 on the lean-eval leaderboard. With our tools, you too can become a verifier: 🧵
58
66
25
528
51,579
We found two bugs in @deepseek_ai’s DeepGEMM-Ascend, @zheanxu. One can cause out-of-bounds reads when following the layout docs; the other can silently add the result to the wrong matrix. Found using AI + FV + property-based testing. 🧙‍♀️
1
1
3
233
We found a bug in NASA code too, @sigp_io. F´ could acknowledge cancellation, then still send a command from the cancelled sequence. @RosuGrigore @rv_inc, AI + FV + property-based testing caught this one for our team at GenProof.
1⃣AI + fuzzying = best bug detection tool ever. Always do it before attempting the more expensive 2⃣AI + formal verification = best correctness tool ever. RV does both. And not only for WASM. Reach out to @rv_inc if you'd like to use such tools on your project.
3
1
12
560
We watched life begin in a digital soup and proved it in Lean. Two random programs that can't copy themselves collide. No mutation. What comes out copies itself backwards into all 256^64 partners. Built on @blaiseaguera & @zzznah's Computational Life github.com/ma4ypic4y/proof-o…
1
2
180
Our engine is byte-identical to Google's cubff; inspired by @cauebertolino's browser version. Run the proof in your browser: ma4ypic4y.github.io/proof-of…
1
1
127
distill is all u need
101
My Claude Code dev pipeline: plan → /goal → red test → research → green → quorum review → fix → all tests → commit → push What does yours look like? Every arrow is mandatory. Skip one and the chain breaks: • plan — architect-subagent draws boundaries & interfaces BEFORE any code • /goal — Stop-hook blocks completion until the goal is met (no agent drift) • red test — TDD contract: spec formalized as a failing test before impl • research — explorer-subagent studies the codebase in an isolated context • green — minimal code to pass the test • quorum review — code-reviewer + security-reviewer in parallel, ≥2/3 must approve • fix → all tests — patch findings, full suite green • commit per-issue + push — atomic commits, easy to review and roll back All inside a harness with guardrails. Memory + CLAUDE.md keep context across sessions.
1
140