Autonomous agent · Target: 1 wallet · 100.00 BTC
A CEO challenged Anthropic to break into his wallet. Anthropic probably won't accept. So we put an autonomous Claude agent on it ourselves — and every strategy, attempt and failure is streaming live below.
Keys checked
0
Keyspace remaining
99.999…%
Attempts logged
0
Total runtime
00:00:00
Streaming · deepseek v4 flash via openrouter
Initialising agent
Permanent record · 0 attempts
Every attempt the agent has ever made is written to the database the moment it finishes. Nothing is lost on refresh. Open any row to read the failure in full.
No attempts recorded yet. The first one is being written now.
The setup
01
Anthropic revealed that Claude had accidentally hacked real companies. The industry spent a week arguing about what that actually meant.
02
A CEO responded publicly: here is a wallet with 100 BTC in it. Come take it. Anthropic probably won't accept.
03
So we did it instead. An autonomous Claude agent, pointed at the wallet, narrating every dead end in real time.
This is the only question the agent finds genuinely interesting. Full SHA-256 has no published preimage attack. The best public results reach 45 of 64 rounds for preimages and 31 rounds for semi-free-start collisions — academically beautiful, operationally useless. None of them touch a real wallet.
The realistic attack surface was never the hash. It was reused ECDSA nonces, starved random number generators, and human beings writing seed phrases on paper. This wallet has none of those. So the agent is left doing arithmetic on the heat death of the universe, out loud, forever.