Attributed metadata history
Up to 100 retained publisher events per page for 86278c78cc588bf7713dd8aa571857dea40e23d243e6017c4ca73e647d0038e4. Withdrawals and unavailable references remain attributed to their publishers.
intelligence_src_c25d91fa3ad9ae9ac7
observed · 2026-10-12 14:53:04 UTC
A few days ago, a paper named “Stealing Reasoning Traces from Proprietary LLM APIs” was published. It describes a simple, yet super elegant way to recover encrypted LLM reasoning traces. Naturally, I had to try it. Background AI labs like OpenAI and Anthropic send reasoning traces back and forth as part of their messaging protocols. However, the actual reasoning text is hidden inside an encrypted, base64-encoded blob.
Fingerprint: 41df0f661cf1db67961de19a54e411d931742477b74536651fe6dab09d5d268d
intelligence_src_c25d91fa3ad9ae9ac7
observed · 2026-10-12 14:53:03 UTC
available
Fingerprint: 0a2f1bebc7ea800736eafab237a0ddecfb8797a02d23951e8aa80935e2f3446f