Stealing Reasoning Traces from Proprietary LLM APIs
Alexander Panfilov@kotekjedi_mlWe can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company.
- ▪Alexander Panfilov@kotekjedi_mlWe can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company.
3 outlets in our directory ran this story, first to last over 7 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ Stealing Reasoning Traces from Proprietary LLM APIs — Stolen-thoughts
- ▪ Stealing Reasoning Traces from Proprietary LLM APIs — arXiv.org
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,443 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | X (formerly Twitter) |
| Canonical URL | https://twitter.com/kotekjedi_ml/status/2087147042888114428 |
| Publication time | Tue, 11 Aug 2026 13:50:33 +0000 |
| Retrieval time | 2026-08-11T13:55:44.227Z |
| Last seen | 2026-08-11T13:55:44.227Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | I1QTndvNqB9Q · 4 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Alexander Panfilov@kotekjedi_mlWe can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company. We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried.12:00 PM · Aug 11, 2026!function(options){var element=document.getElementById(options.targetId);if(!element)return;var cached=document.querySelector('[data-timezone]');var timeZone=cached&&cached.dataset.timezone||Intl.DateTimeFormat().resolvedOptions().timeZone;element.dataset.timezone=timeZone;element.textContent=(function formatFullTimestamp({ timestamp, lang = "en", timeZone }) { const date = new Date(timestamp); let zone = timeZone; if (zone) try { new Intl.DateTimeFormat("en", {…
Excerpt limited to ~120 words for fair-use compliance. The full article is at X (formerly Twitter).
Discussion
0 commentsMore from X (formerly Twitter)
