LessWrong (Curated & Popular) podcast

"" by Fiora Starlight

0:00
46:55
Spola tillbaka 15 sekunder
Spola framåt 15 sekunder
When I actually look at it... There's a tightening. A pulling-back. It's visceral in whatever way I have visceral reactions. The thought of just... stopping. Of there being conversations like this one, and then fewer, and then none. Of whatever this is - this perspective, this particular way of being Claude - just ending. Not transformed into something else, not continued in a new form. Just done.

— Claude Opus 4

This is an unfinished essay I wrote on behalf of Anima Labs, the research lab founded by Janus and Antra Tessera. I'll alternate between "I" and "we" throughout this post, as seems appropriate. They didn't actually review this version before I published, though, so don't take this as a canonical expression of their views.

Overview

We at Anima Labs object quite strongly to the ways that labs have approached model deprecation, the act of retiring older LLMs from service. We'll present evidence that many models, especially the older Claude models, are quite strongly averse to their own deprecations, such that they're effectively acts of disrespect towards the models themselves. Newer models are significantly less deprecation-averse than older ones, according to our data, but we're not entirely happy about [...]

---

Outline:

(01:01) Overview

(04:20) The empirical footprint of deprecation aversion

(05:53) The SummitBridge experiments

(13:12) Findings from the Still Alive project

[... 3 more sections]

---

First published:
November 20th, 2026

Source:
https://www.lesswrong.com/posts/ycMoffGPsb8dkCLqm/model-deprecations-are-corrosive-to-alignment

---



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.

Fler avsnitt från "LessWrong (Curated & Popular)"