Tagged "reasoning"
- Pydantic-Deep: Production Deep Agents for Pydantic AI
- AI's Impact on Mathematics Analogous to Car's Impact on Cities
- Local Qwen Models Master Browser Automation Through Iterative Replanning
- Qwen 3.5 122B Demonstrates Exceptional Reasoning for Local Deployment
- Cicikus v3 Prometheus 4.4B – An Experimental Franken-Merge for Edge Reasoning
- How to Install OpenClaw with Ollama (Step-by-Step Tutorial)
- Sarvam Open-Sources 30B and 105B Reasoning Models
- The $1,500 Local AI Setup: DeepSeek-R1 on Consumer Hardware
- Llama.cpp Adds True Reasoning Budget Support
- Experiment: 0.8B Model Self-Improvement on MacBook Air Yields Surprising Results
- Sarvam Open-Sources 30B and 105B Reasoning Models
- Sarvam Open-Sources 30B and 105B Reasoning Models
- Mistral AI Prepares Workflows Integration for Le Chat
- Qwen 3.5 Small Models Released: 0.8B to 9B Parameters Optimized for On-Device Inference
- Claude Opus 4.6 Solves Problem Posed by Don Knuth
- Google Research Finds Longer Chain-of-Thought Correlates Negatively With Accuracy
- Making Wolfram Technology Available as Foundation Tool for LLM Systems
- GLM-5 Becomes Top Open-Weights Model on Extended NYT Connections Benchmark
- Ouro 2.6B Thinking Model GGUFs Released with Q8_0 and Q4_K_M Quantization
- [Release] Ouro-2.6B-Thinking: ByteDance's Recurrent Model Now Runnable Locally
- Why AI Models Fail at Iterative Reasoning and What Could Fix It
- MiniMax Releases M2.5 Model with SOTA Coding and Agent Capabilities
- ByteDance Releases Seed2.0 LLM with Complex Real-World Task Improvements
- Ring-1T-2.5 Released with SOTA Deep Thinking Performance
- Qwen Coder Next Shows Specialized Agent Performance
- Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts