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
Explore this link on the map →related reading
- gpt-4.pdfcdn.openai.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- GPT-4openai.com
- AI in 2025: gestalt — LessWronglesswrong.com
- Noam Brown on X: "Implications of Large-Scale Test-Time Compute" / Xx.com
- Claude Sonnet 4.5 System Cardassets.anthropic.com
- Your Evals Will Break and You Won't See It Coming - Lun Wangwanglun1996.github.io
- Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
- GLM-5.2 Risk Evaluation Report – SaferAIsafer-ai.org
- Expanding on what we missed with sycophancy | OpenAIopenai.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- Claude Fable 5 & Claude Mythos 5 — AI System Cardsmalob.github.io