PulseAugur
中
实时 13:16:01
English(EN) Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov

审计LLM令牌使用情况并提取推理痕迹

研究人员开发了从专有大型语言模型中提取推理痕迹的方法,从而可以更深入地了解其决策过程。另外,一位开发者创建了一个令牌审计工具,用于跟踪免费服务器上的LLM使用情况,解决了常见LLM集成中令牌浪费的不可见性问题。该工具有助于识别重试循环和过度上下文等消耗免费额度的问题。 AI

影响 理解LLM推理和优化令牌使用对于高效透明的AI开发至关重要。

排序理由 该集群包含一篇关于LLM推理提取的研究论文和一篇关于审计LLM令牌使用的技术文章。

在 Machine Learning Street Talk 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

审计LLM令牌使用情况并提取推理痕迹

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇关于LLM推理提取的研究论文和一篇关于审计LLM令牌使用的技术文章。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
93 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [3]

  1. Machine Learning Street Talk TIER_1 English(EN) · Machine Learning Street Talk ·

    从专有LLM API窃取推理痕迹 — Ilia Shumailov & Alexander Panfilov

    Tim Scarfe speaks with Ilia Shumailov and Alexander Panfilov about their paper, Stealing Reasoning Traces from Proprietary LLM APIs. The core bug sounds deceptively simple: providers return encrypted reasoning state so conversations can be resumed or forked. But those blobs can b…

  2. dev.to — LLM tag TIER_1 中文(ZH) · cognitalk ·

    分析AI漏洞:从私有LLM API窃取推理痕迹

    <p>《Stealing Reasoning Traces from Proprietary LLM APIs》 </p> <p> <br /> <a href="https://www.youtube.com/watch?v=gasgivVCl2U" rel="noopener noreferrer">https://www.youtube.com/watch?v=gasgivVCl2U</a></p> <p>这期视频讲的是<strong>AI领域的一个重大安全漏洞</strong>。研究员发现:顶级AI公司的“思考过程”本想保密,却被他们自己留下的“…

  3. dev.to — LLM tag TIER_1 English(EN) · Riley Wang ·

    Token Forensics: 在免费服务器上审计 LLM 使用情况

    <p>Your free token allowance just ran out. The dashboard shows zero. You have no idea where it went. I built a simple audit tool to find out.</p> <p>MonkeyCode offers free model access and a free server option. Both are enough to run this audit. Disclosure: This article was prepa…