This website uses cookies
Read our Privacy policy and Terms of use for more information.
Concepts
Methods/Techniques
Models
Architectures
Infrastructure
Robotics
FMOps
The Org Age of AI
Interviews
AI 101
∇ Guide
AI builds AI
AI Agents
GenAI Unicorns
Infrastructure Unicorns
Community Twist
The History of LLMs
The History of Computer Vision
The History of World Models
Origins "who coined it"
Inference
Attention Span
Froth on the Daydream
Twitter Library
From our partners
Event Calendar
Aug 25, 2026
A new paper found a way to extract the hidden reasoning of models from OpenAI, Anthropic, and Google without breaking the encryption protecting it.
The trick was surprisingly simple. Let’s discuss it – it’s absolutely fascinating! And begs a few questions about our privacy..
Attention Span is here to show you AI isn’t magic. Sometimes the most important part of an AI interaction is the part you never see.
👉 Subscribe for high-signal AI analysis
👉 Instagram https://www.instagram.com/turingpost_tv
👉 TikTok https://www.tiktok.com/@turingpost_tv
👉 More analysis: https://www.turingpost.com/
👉 Interviews: @realturingpost
🔗 Links mentioned
Stealing Reasoning Traces from Proprietary LLM APIs
https://arxiv.org/abs/2608.09867
Stolen Thoughts, project page and decoded examples
https://stolen-thoughts.com/
Matthew Green, “Let’s talk about encrypted reasoning”
https://blog.cryptographyengineering.com/2026/05/29/fooling-around-with-encrypted-reasoning-blobs/
WIRED, “A New Trick Reveals AI Models’ Inner Thoughts”
https://www.wired.com/story/a-new-trick-reveals-ai-models-inner-thoughts/
#AttentionSpan #AI #HiddenReasoning #ChainOfThought #AIReasoning #AISecurity
Turing Post
Oct 9, 2026
Oct 8, 2026
Oct 7, 2026
Oct 6, 2026
Oct 5, 2026
Sep 14, 2026
Sep 13, 2026
Sep 9, 2026
Sep 4, 2026
Aug 31, 2026