Urgent.News

What's breaking now, across thousands of outlets.

More in AI

Stealing AI Reasoning Traces

Interesting research: “ Stealing Reasoning Traces from Proprietary LLM APIs “: Abstract: Leading large language model providers now conceal their models’ step-by-step reasoning, or chain-of-thought…

  • Proprietary LLM providers conceal reasoning steps as encrypted blocks.
  • Researchers discovered interchangeable encrypted reasoning blocks across sessions and models.

More from Tuesday 8 September →