Why Frontier AI Labs Fight to Hide Chain of Thought — Ilia Shumailov & Alexander Panfilov - YouTube

Follow along using the transcript.

Tim Scarfe speaks with Ilia Shumailov and Alexander Panfilov about their paper, Stealing Reasoning Traces from Proprietary LLM APIs. The core bug sounds deceptively simple: providers return encrypted reasoning state so conversations can be resumed or forked. But those blobs can be replayed across users and sibling models. A smaller model can ask the provider to decrypt the trace, then repeat the hidden reasoning in plain text. The discussion covers leaked private data, a broadly reusable jailbreak, poisoned agent traces, chain-of-thought monitoring, responsible disclosure, and possible…

saved by

• Ishaan Panigrahi

related reading

• Stealing Reasoning Traces from Proprietary LLM APIsresearch.snyk.io
• Stolen Thoughtsstolen-thoughts.com
• Let’s talk about encrypted reasoningblog.cryptographyengineering.com
• Why Sam Altman is against a single superintelligenceyoutube.com
• Recursive Language Models — Alex Zhang, MIT PhDyoutube.com
• AI researchers debate how close we are to recursive self-improvementyoutube.com
• What I learned this week - Can distillation be stopped, Mythos and the cybersecurity equilibrium, Pipeline RLdwarkesh.com
• The fragile foundations of CoT monitoring | Christopher Pottsweb.stanford.edu
• [2608.09867] Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
• Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
• [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org