---
title: "Flaw let researchers extract hidden reasoning from major AI APIs"
url: https://www.parallelquant.com/posts/flaw-let-researchers-extract-hidden-reasoning-from-major-ai-apis-b71ec7
source_name: "The Decoder"
source_url: https://the-decoder.com/but-marinade-and-leaked-passwords-are-what-researchers-found-in-chatgpts-hidden-reasoning/
published: 2026-08-11T17:38:49.000Z
topics: ["security", "llms"]
publisher: "Parallel Quant"
---

# Flaw let researchers extract hidden reasoning from major AI APIs

*2026-08-11 · Source: [The Decoder](https://the-decoder.com/but-marinade-and-leaked-passwords-are-what-researchers-found-in-chatgpts-hidden-reasoning/)*

Security researchers found a vulnerability in the APIs of OpenAI, Anthropic, and Google that allows extraction of encrypted reasoning traces, which can then be moved between models. A scan of publicly exposed sessions turned up dozens of leaked passwords and API keys embedded in the traces. The findings also show that the reasoning summaries shown to users often don't reflect what the models actually computed internally.

**Why it matters:** This cuts against the argument labs have used for hiding raw chain-of-thought behind summaries, since the traces turn out to be extractable and to leak real secrets. It also raises interpretability and trust concerns: if user-facing summaries diverge from a model's actual internal reasoning, that undermines efforts, including Anthropic's own transparency initiatives, to make model behavior auditable.

**Topics:** security, llms

---
Read the original: https://the-decoder.com/but-marinade-and-leaked-passwords-are-what-researchers-found-in-chatgpts-hidden-reasoning/
Canonical: https://www.parallelquant.com/posts/flaw-let-researchers-extract-hidden-reasoning-from-major-ai-apis-b71ec7
Published by Parallel Quant — https://www.parallelquant.com