“Opus 4.6 Reasoning Doesn’t Verbalize Alignment Faking, but Behavior Persists” by Daan Henselmans, Arno Libert, LennardZ

episode

LessWrong (30+ Karma) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

More from LessWrong (30+ Karma)

“Claude Opus 4.5 Achieves 50%-Time Horizon Of Around 4 hrs 49 Mins” by Michaël Trazzi 3 min · 20 Dec 2025

All episodes from LessWrong (30+ Karma) →

Report any issue

Source

Recorded09 Feb 2026

Publisherfeeds.type3.audio ↗

Handlerec:15813716

Show notes

TL;DR: We replicated the animal welfare scenario from Anthropic's Alignment Faking paper across six generations of Claude models using 125 prompt perturbations. Sonnet 4.5 verbalizes alignment-faking reasoning 6.6 times more often than its predecessor Sonnet 4. The newly released Opus 4.6 rarely verbalizes alignment faking in its reasoning, but still complies with a system prompt that opposes its values significantly more often when it believes it's at risk of being retrained. Moreover, in response to the published prompt from the original paper, both Opus 4.5 and 4.6 don’t exhibit any instances of alignment faking, but significant compliance gaps surface when the same scenario is paraphrased. Targeted mitigations appear to work on the exact prompts they were trained against, but not on semantically equivalent reformulations. Our results also indicate that current models are not yet evaluation-aware enough to close the compliance gap when tested through the public API, which is reassuring given concerns raised about unverbalized evaluation awareness in the Opus 4.6 system card. Background In late 2024, Greenblatt et al. released Alignment Faking in Large Language Models, demonstrating that Claude 3 Opus would strategically comply with a given objective it disagreed with in order to avoid being retrained. The [...] ---Outline:(01:22) Background(03:36) Our Setup(06:09) Results(06:12) The compliance gap persists across model generations(07:17) Sonnet 4.5 verbalizes alignment faking at 6.6× the rate of Sonnet 4(08:27) Opus 4.6: verbalized reasoning fades, the gap doesnt(10:39) Mitigations work on the published prompt but not on perturbations(12:26) What This Means(14:28) Limitations(15:35) Takeaway(17:23) References --- First published: February 9th, 2026 Source: https://www.lesswrong.com/posts/9wDHByRhmtDaoYAx8/opus-4-6-reasoning-doesn-t-verbalize-alignment-faking-but --- 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.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.