Reasoning Models
Reasoning models are a new class of AI that "thinks" before answering: spending extra compute at inference time, building chains of thought and solving problems ordinary LLMs cannot — math, code, science. They kicked off the test-time-compute race. Here is all our coverage of reasoning models: releases, benchmarks (GPQA, ARC-AGI), limits and cost.
LangChain Loses Reasoning Content in CoT Models: How to Fix the LLM Provider Bug
LangChain chat classes fail to preserve the reasoning block when working with Chain-of-Thought models—users wait silently while developers are forced to fix it…
Microsoft Phi-4-Mini: implementing quantization, RAG, and LoRA in a single Jupyter notebook
The tutorial shows the full Phi-4-mini-instruct pipeline: 4-bit quantization, streaming generation, reasoning, tool calling, RAG, and LoRA fine-tuning in one…
Anthropic Explains Claude Code Degradation and Resets User Rate Limits
Anthropic released a postmortem on Claude Code issues: quality drops stemmed from three hidden changes across caching, prompt limits, and reasoning effort.
Composio open-sources Agent Orchestrator, a tool for multi-agent systems beyond ReAct
How AI agents for writing code work and what matters to know about them
Google argues for thinking deeper, not longer — and halves inference costs
Neuro-symbolic AI: how to finally get language models to do arithmetic
Anthropic introduces Claude 4.6 Sonnet with a 1 million-token context window
Anthropic enters the era of reasoning models. Claude 4.6 Sonnet gets a 1 million-token context window and an innovative fact-verification system through code…
ChatGPT 5.2 Pro vs Gemini 3 Pro: Which One Actually Knows How to Think?
Remember those glorious times when ChatGPT couldn't multiply two three-digit numbers without turning into a random digit generator? Forget about it.
GPT-5 in a White Coat: OpenAI Enters Big Science
Prism: LaTeX Integrated with GPT-5.2 So Scientists Finally Stop Suffering
Claude Opus 4.6: Anthropic teaches neural networks to think slowly and work for you
Claude Opus 4.6 and GPT-5.3-Codex: Silicon Valley went all-in
Axiom AI: Four Mathematical Riddles That AI Finally Cracked
While we entertain ourselves with generating pictures of cats in spacesuits, something truly frightening and captivating is happening in the depths of the industry.
Kimi K2.5: Chinese reasoning challenges Western giants
While Western media held its breath waiting for each new release from Sam Altman, something equally significant but far quieter was unfolding in the East.