Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
4 results for “reasoning traces”
Researchers find that feeding a frontier model's encrypted reasoning traces to a weaker model from the same provider can make it output the traces in plaintext (Will Knight/Wired)
Researchers demonstrated a method to extract plaintext 'reasoning traces' from encrypted internal outputs of frontier LLMs like Claude, GPT, and Gemini by feeding those encrypted traces to weaker models from the same provider.
Aug 12, 2026
A New Trick Reveals AI Models’ Inner Thoughts
Researchers developed a method to extract internal reasoning traces from major US AI models and claim the resulting patterns suggest some Chinese AI models were trained on those US models' outputs.
Aug 11, 2026
DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification
A research team introduced two methods for verifying numerical claims in English and Arabic using LLM-based trace ranking and grouped reward modeling, achieving mixed results across metrics and languages.
Jul 29, 2026
When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
A theoretical paper introduces a sampling-complexity framework to explain when and why in-context search—iterative generation, critique, and revision in LLMs—yields exponential performance gains over zero-shot reasoning.
Jul 10, 2026