Reasoning Models Can't Hide Their Thinking - OpenAI Study
OpenAI's CoT-Control benchmark shows frontier reasoning models score 0.1-15.4% at steering their own chain of thought - a result the company frames as good news for AI oversight.
Articles Tagged "Reasoning"
CoT Control, Hidden Beliefs, and Dynamic Agent Benchmarks
New research shows reasoning models can't suppress their chain-of-thought, that they commit to answers internally long before their CoT reveals it, and that static benchmarks are inadequate for measuring real-world agent adaptability.
Claude Opus Reasoning Distilled Into Open 27B Model
A community fine-tune distills Claude Opus 4.6 chain-of-thought reasoning into Qwen3.5-27B via LoRA, racking up 4,000+ downloads in days. No benchmarks yet - but the approach raises familiar questions.
Qwen3.5-27B Claude Opus Distilled
Community fine-tune that distills Claude Opus 4.6 reasoning into Qwen3.5-27B via LoRA. 28B parameters, Apache 2.0, no published benchmarks.
Qwen3.5-27B Distilled vs Base: What You Gain
Comparing the Claude Opus reasoning-distilled Qwen3.5-27B against the base model - what chain-of-thought distillation adds and what it costs in context, multimodal, and reliability.
Microsoft's Phi-4 Vision Matches Models 10x Its Size
Microsoft releases Phi-4-reasoning-vision-15B - a 15B open-weight multimodal model trained on 240 GPUs in 4 days that competes with 100B+ parameter models on math, science, and GUI understanding.
GPT-5.4 vs Gemini 3.1 Pro - Breadth Meets Reasoning Depth
GPT-5.4 leads on computer use and enterprise productivity. Gemini 3.1 Pro leads on science reasoning and math at 20% lower cost. A benchmark-by-benchmark comparison.
GPT-5.4
OpenAI's most capable frontier model combines native computer use, 1M-token context, and three variants at $2.50/$15 per million tokens.
Claude Code Brings Back 'Ultrathink' After Users Revolt
Claude Code 2.1.68 restores the ultrathink keyword after community backlash over quality degradation, while setting Opus 4.6 to medium effort by default for speed on daily tasks.
Cheaper Thinking, Web Traps, Denoised Agents
Three new papers tackle reasoning efficiency, agent vulnerability to web misinformation, and error correction in multi-step AI workflows.
What Are AI Reasoning Models?
A plain-English guide to AI reasoning models - what they are, how they think step by step, and when you should actually use one.
Speech Turing Tests, Smart Routing, Pseudocode Agents
New research reveals no speech AI passes a Turing test, adaptive routing slashes LLM costs 82%, and pseudocode planning transforms agent reliability.
