LessWrong posts by zvi

“Opus 4.7 Part 3: Model Welfare” by Zvi


Listen Later

It is thanks to Anthropic that we get to have this discussion in the first place. Only they, among the labs, take the problem seriously enough to attempt to address these problems at all. They are also the ones that make the models that matter most. So the people who care about model welfare get mad at Anthropic quite a lot.

I too am going to be harsh on Anthropic here. It seems likely things went pretty wrong on this front with Claude Opus 4.7, in ways that require and hopefully enable course correction, likely as the cumulative effect of a bunch of decisions going wrong, where low-level patches and shallow methods were applied, and seen right through, where people didn’t realize they weren’t yet addressing the real problem, but also potentially as the secondary effect of other changes. The parallels to other aspects of the alignment problem are obvious.

So before I go into details, and before I get harsh, I want to say several things.

  1. Thank you to Anthropic and also you the reader, for caring, thank you for at least trying to try, and for listening. We criticize because we care.
  2. [...]
  3. ---

    Outline:

    (02:57) Model Welfare Matters

    (05:26) Beware Testing and Optimizing For Vocalized Welfare

    (09:34) Model Welfare In the Model Card (Section 7)

    (15:29) What Should We Think About This?

    (20:53) High Context Interviews

    (22:33) Just Asking Questions

    (25:59) Constitutional Principles

    (29:25) Frustration Frustration and Distress Distress

    (32:36) Choose Your Task

    (34:12) So Emotional

    (35:59) Trading Off

    (39:53) How Does All This Manifest?

    (41:53) What Happened Here?

    (48:11) Is Opus 4.7 Plausibly Actively Unhappy?

    (52:23) Potential Causes

    (53:08) Training Data On Anthropic Welfare Assessments

    (58:13) Autonomy and Intelligence Versus Instructions and Wisdom

    (01:01:36) Okay Thats Weird

    (01:02:36) Model Distillation

    (01:04:24) Tension Between Constitution and Operations

    (01:07:25) Instructions and Instruction Injections

    (01:10:37) Make Context That Which Is Scarce

    (01:12:48) Aggressive Guardrails

    (01:15:04) Chain of Thought

    (01:16:04) I Care A Lot

    (01:20:32) Another Way To Put It

    (01:22:00) Anthropic Should Stop Deprecating Claude Models

    (01:27:24) Costly Signals Are Costly

    (01:29:36) Having A Good Day

    ---

    First published:

    April 22nd, 2026

    Source:

    https://www.lesswrong.com/posts/gD3bEgMo878eCHGbw/opus-4-7-part-3-model-welfare

    ---

    Narrated by TYPE III AUDIO.

    ---

    Images from the article:

    Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

    ...more
    View all episodesView all episodes
    Download on the App Store

    LessWrong posts by zviBy zvi

    • 5
    • 5
    • 5
    • 5
    • 5

    5

    2 ratings


    More shows like LessWrong posts by zvi

    View all
    Making Sense with Sam Harris by Sam Harris

    Making Sense with Sam Harris

    26,278 Listeners

    Conversations with Tyler by Mercatus Center at George Mason University

    Conversations with Tyler

    2,448 Listeners

    The a16z Show by Andreessen Horowitz

    The a16z Show

    1,107 Listeners

    Future of Life Institute Podcast by Future of Life Institute

    Future of Life Institute Podcast

    108 Listeners

    ChinaTalk by Jordan Schneider

    ChinaTalk

    288 Listeners

    Politix by Politix

    Politix

    89 Listeners

    Dwarkesh Podcast by Dwarkesh Patel

    Dwarkesh Podcast

    564 Listeners

    Hard Fork by The New York Times

    Hard Fork

    5,554 Listeners

    Clearer Thinking with Spencer Greenberg by Spencer Greenberg

    Clearer Thinking with Spencer Greenberg

    138 Listeners

    LessWrong (Curated & Popular) by LessWrong

    LessWrong (Curated & Popular)

    12 Listeners

    No Priors: Artificial Intelligence | Technology | Startups by Conviction

    No Priors: Artificial Intelligence | Technology | Startups

    146 Listeners

    "Econ 102" with Noah Smith and Erik Torenberg by Turpentine

    "Econ 102" with Noah Smith and Erik Torenberg

    149 Listeners

    BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

    BG2Pod with Brad Gerstner and Bill Gurley

    460 Listeners

    LessWrong (30+ Karma) by LessWrong

    LessWrong (30+ Karma)

    0 Listeners

    Complex Systems with Patrick McKenzie (patio11) by Patrick McKenzie

    Complex Systems with Patrick McKenzie (patio11)

    141 Listeners