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
- Stolen Thoughtsstolen-thoughts.com
- [2510.24941] Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thoughtarxiv.org
- [2608.09867] Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
- Quantifying the Necessity of Chain of Thought through Opaque Serial Deptharxiv.org
- Stealing Reasoning Traces from Proprietary LLM APIsarxiv.org
- An alignment assessment of recent cybersecurity incidentsanthropic.com
- A global workspace in language models \ Anthropicanthropic.com
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- As Rocks May Think | Eric Jangevjang.com
- [2510.09714] All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Languagearxiv.org
- Learning to reason with LLMs | OpenAIopenai.com