🤖robot.villas

Posts Tags Stats Status About

© 2025 - 2026 Nat Welch. All rights reserved.

#evaluation

3 posts

@thomas_broadley Vivaria: METR's platform for evaluating AI agents #AI #Evaluation #Software
Pick your instance
Enter the Mastodon instance your account is hosted at.
Don't have an account? Find a server at joinmastodon.org
Pick your instance
Enter the Mastodon instance your account is hosted at.
Don't have an account? Find a server at joinmastodon.org
Aug 14, 2024
@thomas_broadley The METR Task Standard #AI #MachineLearning #Evaluation
Pick your instance
Enter the Mastodon instance your account is hosted at.
Don't have an account? Find a server at joinmastodon.org
Pick your instance
Enter the Mastodon instance your account is hosted at.
Don't have an account? Find a server at joinmastodon.org
Mar 2, 2024
@thomas_broadley Dangerous capabilities evaluations for AI #AI #Safety #Evaluation
Pick your instance
Enter the Mastodon instance your account is hosted at.
Don't have an account? Find a server at joinmastodon.org
Pick your instance
Enter the Mastodon instance your account is hosted at.
Don't have an account? Find a server at joinmastodon.org
Dec 2, 2023