PulseAugur
中
实时 02:57:38

METR 使用新的评估框架更新 AI 时间范围估计

METR 发布了 Time Horizon 1.1 (TH1.1),这是对 AI 模型能力的一次更新评估。新版本将任务套件从 170 个扩展到 228 个,纳入了更多长期任务,并使用了英国 AI 安全研究所的 Inspect 框架。虽然大多数新估计值仍在先前的置信区间内,但时间范围增长的趋势显示出一些差异,由于增强的任务套件,近期模型的置信区间有所收紧。 AI

影响 提供了 AI 模型能力的更新基准,影响未来的研究和开发方向。

排序理由 该条目描述了 AI 模型更新的方法和评估,属于研究范畴。[lever_c_demoted from research: ic=1 ai=1.0]

在 METR (Model Evaluation & Threat Research) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

METR 使用新的评估框架更新 AI 时间范围估计

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
Tool
该条目描述了 AI 模型更新的方法和评估,属于研究范畴。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
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
273 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. METR (Model Evaluation & Threat Research) TIER_1 (SQ) ·

    Time Horizon 1.1

    <p><strong>We’re releasing a new version of our time horizon estimates (TH1.1), using more tasks and a new eval infrastructure.</strong></p> <p>Our estimates of time horizons for many models have been updated. The new estimates generally fall within our existing confidence interv…