not much happened today

**Anthropic** launches "Claude in Excel Pro" with enhanced features. **OpenAI** reveals upcoming **Codex** agent loop and cybersecurity measures. **Google** boosts **Gemini App** quotas and partners with **Sakana AI** for advanced AI Scientist projects in Japan. **Cursor** introduces Agent Skills for dynamic context focus. **GPT-5.2 Pro** achieves **31%** on FrontierMath Tier 4, showing significant benchmark progress. **Baseten** raises **$300M** at a **$5B valuation** targeting high-performance inference. Discussions highlight math benchmarks as indicators of AI capability, uneven AGI progress, and the importance of reasoning and continual learning as future frontiers. Notable figures include *Sam Altman*, *François Chollet*, *Shane Legg*, and *Demis Hassabis*.