Jonas Geiping

A new paper demonstrates that encrypted reasoning traces from frontier AI models can be decoded and replayed to improve open models, with a scan of ~7,000 public traces revealing 62 unique API keys, 3…

A new paper by Alexander Panfilov, Ilia Shumailov, Luca Beurer-Kellner, Jonas Geiping, Maksym Andriushchenko and colleagues demonstrates that encrypted reasoning traces from proprietary LLM APIs from …

A new preprint, 'Stealing Reasoning Traces from Proprietary LLM APIs,' reveals that encrypted chain-of-thought blocks from Anthropic, OpenAI, and Google can be replayed into weaker sibling models to e…