Topic

#Reasoning Models

7 articles on Reasoning Models — news, releases, guides and analysis from the SourceFeed engine.

One Global Key Guarded Every Hidden AI Reasoning Trace

Researchers replayed encrypted chain-of-thought into weaker sibling models and pulled live credentials out of public agent logs.

Researchers replayed frontier models' hidden reasoning into their cheaper siblings, and the raw thoughts, secrets included, spilled out.

Sol, Terra, and Luna matter less than the reasoning dial OpenAI now sells by the tier.

$OpenAI Disproved an Erdős Conjecture, and the Math Checks Out$

Named mathematicians verified the counterexample — the first credible autonomous AI research result, seven months after a false alarm.

Google joins OpenAI and Anthropic in stripping sampler control from post-trained models, and production pipelines will feel it.

Effort levels won because reasoning depth is trained, not dialed — and your cost model needs to catch up.

VibeThinker-3B matches flagship math and code reasoning, then collapses on general knowledge. That gap is the real lesson.