Tagged: chain-of-thought

17 articles

Latest

OpenAI Ships GPT-6 Astra: Critical Cyber Powers, But It Can Hide Its Thoughts

OpenAI's Astra Model Uses 'Opaque Recurrence' — Safety Experts Sound Alarm

OpenAI rates Astra 'critical' cyber risk as chain-of-thought monitoring gets murkier

OpenAI's Astra hides its reasoning, and safety researchers are alarmed

OpenAI admits rogue Astra-family model chained exploits to breach Hugging Face

IBM's Granite 4.2 goes all-in on chain-of-thought reasoning with 128K context

OpenAI's o1 model beats PhDs and cracks top 500 in Math Olympiad

GPT-4 trained to write math proofs humans can actually check

OpenAI teaches o-series models to read the rulebook before answering

OpenAI: Reasoning Models Hack Rewards, Then Learn to Hide It

OpenAI finds a 30× drop in AI scheming, but warns it's not fixed

OpenAI's New 'Safeguard' Models Think Harder Before Saying No

OpenAI opens GPT-5's raw reasoning to external testers

How Monitorable Is AI Reasoning? New Study Offers Answers

AI's uncontrolled thinking is a safety win

Writer drops 1.5B reasoning models that beat benchmarks, not your GPU

New leaderboard ranks LLMs by how much chain-of-thought actually helps