The current SOTA model was released without safety evals — LessWrong

TL;DR: OpenAI released GPT-5.4 Thinking and GPT-5.4 Pro on March 5, 2026. GPT-5.4 Pro is likely the best model in the world for many catastrophic ris…

x The current SOTA model was released without safety evals — LessWrong AI Evaluations AI Risk OpenAI AI Practical World Modeling Personal Blog 2026 Top Fifty: 14 % 110 The current SOTA model was released without safety evals by Parv Mahajan , yeedrag 8th Mar 2026 6 min read 12 110 TL;DR: OpenAI released GPT-5.4 Thinking and GPT-5.4 Pro on March 5, 2026. GPT-5.4 Pro is likely the best model in the world for many catastrophic risk-relevant tasks , including biological research R&D, orchestrating cyberoffense operations, and computer use. GPT-5.4 Pro has no system card , only GPT-5.4 Thinking, an

related reading

• gpt-4.pdfcdn.openai.com
• GPT-5.6 Preview System Card - OpenAI Deployment Safety Hubdeploymentsafety.openai.com
• GPT-5.6 Preview System Carddeploymentsafety.openai.com
• Claude Mythos Preview System Cardwww-cdn.anthropic.com
• Summary of METR's predeployment evaluation of GPT-5.6 Solmetr.org
• GPT-4openai.com
• AI in 2025: gestalt — LessWronglesswrong.com
• Claude Opus 4.5: Model Card, Alignment and Safetythezvi.substack.com
• GPT-6 Astra System Card - OpenAI Deployment Safety Hubdeploymentsafety.openai.com
• A Safe Path to Open Weights - Thinking Machines Labthinkingmachines.ai
• GPT-6 Astra System Carddeploymentsafety.openai.com
• GPT-5.5 and the broken state of government evalstransformernews.ai