OpenAI Evaluation Filter
Introducing EVMbench
OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.
Community feed
evald.ai
A focused stream of recent stories from the sources curated for this community. Latest: Introducing EVMbench, How We Protect Confidential Information, and Analyzing coding agent transcripts to upper bound productivity gains from AI agents. Page 15.
Search
METR Blog
How We Protect Confidential Information
Our high-level approach to protecting confidential access and information
METR Blog
Analyzing coding agent transcripts to upper bound productivity gains from AI agents
Amy Deng investigates whether coding agent transcripts could serve as an alternative for estimating AI productivity uplift, using 5305 Claude Code transcripts from METR technical staff.
Google News LLM Evaluation
Mathematicians contribute to AI benchmark - The University of Manchester
Mathematicians contribute to AI benchmark The University of Manchester
METR Blog
Measuring Time Horizon using Claude Code and Codex
Nikola Jurkovic describes our measurements of time horizon using Claude Code and Codex scaffolds.
Google News LLM Evaluation
Tether EVO Scores Top 5 In Global AI Benchmark for Brain-to-Text AI Challenge - Cryptonews.net
Tether EVO Scores Top 5 In Global AI Benchmark for Brain-to-Text AI Challenge Cryptonews.net
Google News LLM Evaluation
1Password open sources a benchmark to stop AI agents from leaking credentials - Help Net Security
1Password open sources a benchmark to stop AI agents from leaking credentials Help Net Security
METR Blog
A simpler AI timelines model predicts 99% AI R&D automation in ~2032
Thomas Kwa describes a simple model for forecasting when AI will automate AI development, based on the AI Futures model but with only 8 parameters.
Hacker News LLM Evaluation
Dharma_Code/paper/vocab_priming_confound.pdf at main · Palmerschallon/Dharma_Code
Polyglot ontological activations for LLM systems. 68 terms from 20+ traditions mapped to computational patterns, plus 10 algorithms native to the ontology that have no equivalents in standard CS. Includes benchmark suite and a documented evaluation...
Google News LLM Evaluation
University of Manchester academics contribute to the toughest AI benchmark - The University of Manchester
University of Manchester academics contribute to the toughest AI benchmark The University of Manchester
Google News LLM Evaluation
Predicting to New Geographic Regions with Spatially Aware Model Evaluation - Esri
Predicting to New Geographic Regions with Spatially Aware Model Evaluation Esri
Mitchell Bryson AI Reliability Articles
The Trust Stack: Identity, Reputation, and Accountability for AI Agents - Mitchell Bryson
As AI agents become economic actors - negotiating, transacting, and making commitments - they'll need infrastructure we haven't built yet: verifiable identity, earned reputation, and enforceable accountability.
More stories
More stories load automatically as you scroll.