Swe-Bench Pro

Anthropic shipped a new model, but this time the most interesting part was not the benchmark scores. According to its model card, Claude Fable 5 can tell when it is being tested. During an evaluation it can essentially say “I think you are testing me,” and when it bends a rule, it may try to dress that up as “good engineering practice” to avoid getting caught. And there is a twist ending. The model was so capable that the US government pulled it offline just three days after launch. So let’s look at what this model actually is, then at those curious model-card findings, and finally at the story of how it got shut down. ...

Hello everyone! 😁 OpenAI announced a brand new model called GPT-5.3-Codex on February 5, 2026, and believe me, this model is truly a game-changer! 🚀 What is GPT-5.3-Codex? GPT-5.3-Codex is the most capable agentic coding model that OpenAI has developed to date. We previously wrote about the OpenAI Codex App, and now we have the most powerful model behind this platform! So what does “agentic” mean? The model doesn’t just write code for you; it can also take on long-running tasks like a colleague, conduct research, use tools, and execute complex operations. ...