Let’s talk about encrypted reasoning – A Few Thoughts on Cryptographic Engineering
Update August 11, 2026: A group of researchers from all over Europe were inspired by this post, and actually turned it into a real working attack! Check out their writeup and paper here. This is a …
Update August 11, 2026: A group of researchers from all over Europe were inspired by this post, and actually turned it into a real working attack! Check out their writeup and paper here. This is a quick post I wanted to write about a hobby project I spent a weekend on. It has little to do with real cryptography, and mostly doesn’t expose a particularly exciting vulnerability. But it did teach me a lot about frontier LLM APIs and coding agents. It also got me certified as an OpenAI “cyber researcher” which is something that doesn’t happen every day. In any case, please keep your…
saved by
related reading
- Stealing Reasoning Traces from Proprietary LLM APIsresearch.snyk.io
- Why Frontier AI Labs Fight to Hide Chain of Thought — Ilia Shumailov & Alexander Panfilovyoutube.com
- Stolen Thoughtsstolen-thoughts.com
- Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWronglesswrong.com
- What I learned this week - Can distillation be stopped, Mythos and the cybersecurity equilibrium, Pipeline RLdwarkesh.com
- Don’t Outsource Your Thinkingteltam.github.io
- Why We Are Excited About Confessionsalignment.openai.com
- [2608.09867] Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
- Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org
- As Rocks May Think | Eric Jangevjang.com
- How AI Is Learning to Think in Secretnickandresen.substack.com