reasoning
Extended thinking, chain-of-thought, test-time compute
Topics
- Claude (Anthropic)Claude is Anthropic's family of models, offered through claude.ai, the Claude API, Claude Code, and cloud platforms (Amazon Bedrock, Google Vertex AI, Microsoft Foundry, and Claude Platform on…
- GPT (OpenAI)OpenAI's GPT models power ChatGPT, Codex, and the OpenAI API. GPT-5 (August 2025) merged the separate GPT and "o-series" reasoning lines into one family. A series of GPT-5.x releases followed…
- Prompting and context engineeringPrompting is writing the instructions and context a model works from. As models have improved, the craft has moved from tricks and magic phrases toward context engineering: choosing what…
- Reasoning models and extended thinkingReasoning models generate internal reasoning ("thinking") before their final answer. Spending more compute at inference time this way improves results on maths, coding, planning, and multi-step…
Sources
- Gemini 4 Argon model page (Gemini API docs)docs · Google · 13 October 2026
- Developing Gemini 4 Argon responsibly and safelyarticle · Anca Dragan and Raluca Ada Popa (Google DeepMind) · 13 October 2026
- Gemini 4 Argon: Built to solve your hardest problemsarticle · Koray Kavukcuoglu (Google DeepMind) · 13 October 2026
- Gemini 4 Argon for Roboticsarticle · Kanishka Rao (Google) · 13 October 2026
- Thinking Inertia: LLMs Keep Thinking When Told Not Topaper · Dianqiao Lei, Kevin Qinghong Lin, Pan Lu, Philip Torr, James Zou · 8 October 2026
- Troubleshooting thinking (Claude API docs)docs · Anthropic
- Claude Haiku 5.5release · Anthropic · 7 October 2026
- Introducing Mistral Large 4release · Mistral AI · 6 October 2026
- Introducing Muse Spark 1.1article · Meta Superintelligence Labs · 9 July 2026
- DeepSeek V4 Preview Releaserelease · DeepSeek · 24 April 2026
- DeepSeek-V4.1-Flash: Smarter, Faster, More Efficientrelease · DeepSeek · 10 September 2026
- ReAct: Synergizing Reasoning and Acting in Language Modelspaper · Yao et al. (Princeton, Google Research) · 6 October 2022
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelspaper · Wei et al. (Google Research) · 28 January 2022