AllFeed, trending, and board
FeedLatest news
TrendingOpen source and releases
BoardBlogs and showcases
TagsBrowse by topic

#evaluation

The latest AI and developer news about #evaluation, with the original source and a short summary.

AI Briefing

Privacy Policy Terms of Service Contact About Sources RSS Support us

Feed
Trending
Tags
Settings

#evaluation - page 2 | AI Briefing

Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents

·2026.05.01 09:00

AISI Evaluates GPT-5.5's Cyber Capabilities

·2026.05.01 08:00

GPT-5.5 Leads in Cyber Evaluation

·2026.05.01 01:00

Qwen-Scope: Decoding Intelligence and Unlocking Potential

·2026.04.30 13:00

DeepMind releases ProEval GitHub repository for GenAI evaluation

·2026.04.30 09:00

Why SWE-bench Verified No Longer Measures Frontier Coding Ability

·2026.04.27 18:00

SWE-bench Contamination Confirmed

·2026.04.27 03:00

Human: Judgment Beyond the Score

·2026.04.23 17:00

Over-editing: The phenomenon where models modify code more than necessary

·2026.04.23 02:00

Part 2: Policy-Following Evaluators, LLM-as-a-Judge

·2026.04.22 09:00

Haiku overtakes Opus

·2026.04.21 23:00

The Machine: How AI Evaluates Code That Uses AI

·2026.04.20 14:00

The Two Faces of OpenClaw

·2026.04.20 09:00

Benchmarking Document Parser Performance

·2026.04.17 05:00

Compiling Evaluations from Context

·2026.04.17 02:00

The Opt-Out Trap

·2026.04.16 11:00

Shocking Variance Across Models

·2026.04.16 03:00

A Verification Hole, Oral

·2026.04.15 15:00

Agents cut in half

·2026.04.15 00:00

How AI Agent Benchmarks Were Broken and What Comes Next

·1·2026.04.12 21:00

Evaluating Netflix Show Synopses with LLM-as-a-Judge

·2026.04.11 01:00

Claw-Eval Benchmark for AI Agents (GitHub Repository)

·2026.04.09 09:00

SWE-bench Verified No Longer Measures Frontier Coding Capability

·2026.04.07 18:00

A New Standard for Agents

·2026.04.02 01:00

Previous
1
2
3
Next

Previous
1
2
3
Next