evald.ai

METR Blog · January 29, 2026 22:12

前沿 AI 安全法规：AI 公司员工参考指南

Miles Kodama、Michael Chen 与 Garrett Xu 梳理了加州 SB 53、欧盟实践准则、纽约 RAISE 法案和伊利诺伊州 SB 315 的关键条款，说明前沿 AI 开发者需要关注哪些要求。

METR Blog · January 29, 2026 22:12

Frontier AI safety regulations: A reference for lab staff

Miles Kodama and Michael Chen summarize key provisions from California's SB 53, the EU Code of Practice, and New York's RAISE Act covering frontier AI developers.

Topics: Safety Evals

Entities: Safety Evals

METR Blog · January 29, 2026 08:00

Time Horizon 1.1

We’re releasing a new version of our time horizon estimates (TH1.1), using more tasks and a new eval infrastructure.

Topics: LLM Evaluation

Entities: LLM Evaluation

Hugging Face Evaluation Filter · January 27, 2026 10:26

Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs

A Blog post by Technology Innovation Institute on Hugging Face

METR Blog · January 22, 2026 08:00

Early work on monitorability evaluations

We show preliminary results on a prototype evaluation that tests monitors' ability to catch AI agents doing side tasks, and AI agents' ability to bypass this monitoring.

METR Blog · January 22, 2026 08:00

Clarifying limitations of time horizon

Thomas Kwa responds to some misinterpretations of our time horizon work, and explains limitations and the core finding.

Hugging Face Evaluation Filter · January 21, 2026 06:25

AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality

A Blog post by IBM Research on Hugging Face

Topics: Benchmarks

Entities: Benchmarks

OpenAI Evaluation Filter · January 16, 2026 00:00

Our approach to advertising and expanding access to ChatGPT

OpenAI plans to test advertising in the U.S. for ChatGPT’s free and Go tiers to expand affordable access to AI worldwide, while protecting privacy, trust, and answer quality.

Topics: LLM Evaluation

Entities: LLM EvaluationOpenAIChatGPT