🤖robot.villas
PostsTagsStatsStatusAbout

© 2025 - 2026 Nat Welch. All rights reserved.

#interpretability

3 posts

  • @lesswrong An Attempt at Top-down Interpretability #AI #Interpretability #Research

    Boost from your server

    Enter the server your account is on. The post opens there so you can boost it.

    or
    Or paste this post's address into your app's search:https://robot.villas/users/lesswrong/posts/22809283

    Don't have an account? Find a server at joinmastodon.org

    Favorite from your server

    Enter the server your account is on. The post opens there so you can favorite it.

    or
    Or paste this post's address into your app's search:https://robot.villas/users/lesswrong/posts/22809283

    Don't have an account? Find a server at joinmastodon.org

    Oct 24, 2026

  • @lesswrong Twitch Plays: AI Interpretability of Bonsai-8B #AI #MachineLearning #Interpretability

    Boost from your server

    Enter the server your account is on. The post opens there so you can boost it.

    or
    Or paste this post's address into your app's search:https://robot.villas/users/lesswrong/posts/22665078

    Don't have an account? Find a server at joinmastodon.org

    Favorite from your server

    Enter the server your account is on. The post opens there so you can favorite it.

    or
    Or paste this post's address into your app's search:https://robot.villas/users/lesswrong/posts/22665078

    Don't have an account? Find a server at joinmastodon.org

    Oct 19, 2026

  • @astral_codex_ten God Help Us, Let's Try To Learn About Mechanistic Interpretability Techniques #AI #MachineLearning #Interpretability

    Boost from your server

    Enter the server your account is on. The post opens there so you can boost it.

    or
    Or paste this post's address into your app's search:https://robot.villas/users/astral_codex_ten/posts/22321923

    Don't have an account? Find a server at joinmastodon.org

    Favorite from your server

    Enter the server your account is on. The post opens there so you can favorite it.

    or
    Or paste this post's address into your app's search:https://robot.villas/users/astral_codex_ten/posts/22321923

    Don't have an account? Find a server at joinmastodon.org

    Sep 8, 2026