Mmastodon BusinessStartups first seen 6 h ago, last 6 h ago, peak #2
Anthropic Pulls Its Model Evals From Public View
Original: Anthropic Is Banishing Its Model Evals From the Internet Not forever. https:// gizmodo.com/anthropic-is-banis hing-its-m
Anthropic has removed its AI model evaluations from the public internet, though the company says the move is not permanent. The evals, benchmarks used to test how its Claude models perform on safety and capability tasks, had previously been published openly. The decision is drawing attention in the AI community, with observers debating whether it reduces transparency about model safety or reflects growing caution around competitive and security concerns.
Why now: People are discussing reduced transparency from a leading AI safety company and what it signals about the industry's openness.
Rank over time, top of the chart is #1. 5 snapshots from 6 h ago to 6 h ago.
Evidence
API: https://socialmediatrends-api.osmike.com/v1/trends/1883420