DeepSeek doing big things
Releases DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4
“We perform a reinforcement learning stage to further enhance its ability to bridge informal reasoning with formal proof construction. Following the standard training objective for reasoning models, we use binary correct-or-incorrect feedback as the primary form of reward supervision.”
“The resulting model, DeepSeek-Prover-V2-671B, achieves state-of-the-art performance in neural theorem proving, reaching
88.9% pass ratio on the MiniF2F-test and solving 49 out of 658 problems from PutnamBench.”
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
Releases DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4
“We perform a reinforcement learning stage to further enhance its ability to bridge informal reasoning with formal proof construction. Following the standard training objective for reasoning models, we use binary correct-or-incorrect feedback as the primary form of reward supervision.”
“The resulting model, DeepSeek-Prover-V2-671B, achieves state-of-the-art performance in neural theorem proving, reaching
88.9% pass ratio on the MiniF2F-test and solving 49 out of 658 problems from PutnamBench.”
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
🔥4🤯3
Wouldn’t be surprised if DeepSeek crushes OpenAI
While OpenAI was filling their ranks with fake email job HR girls, DeepSeek was filling theirs with quants
OpenAI better be looking at buying them out if they want to survive, because they’re in trouble
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
While OpenAI was filling their ranks with fake email job HR girls, DeepSeek was filling theirs with quants
OpenAI better be looking at buying them out if they want to survive, because they’re in trouble
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
💯7👀4
BREAKING: Meta stock, $META, surges over +5% after reporting stronger than expected Q1 2025 earnings
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
🔥4👀3
BREAKING: Microsoft stock, $MSFT, surges over +7% after reporting stronger than expected Q1 2025 earnings
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
🄳🄾🄾🄼🄿🄾🅂🅃🄸🄽🄶
👀4🔥2🤯1