Listen in the Podli app 🎧
Follow your favourite podcasts, listen offline and in the car with CarPlay and Android Auto, and always pick up where you left off. Free to try.
For a while, we felt we had a pretty good grasp over LLM behaviour because we had to exert significant effort to elicit misaligned behaviour. Then, fairly suddenly, we moved to undereliciting misaligned behaviour. Let us recount:
- For a while, there was a bit where safety research seemed to over-elicit bad propensities. A common criticism of papers like Agentic Misalignment was that they basically led the witness using prompting.
- I recall that a paper even as recent as Peer-preservation took similar flak on Twitter.
- But now, we are instead under-eliciting bad propensities, and bad behavior that surfaces is increasingly caught by someone other than the developer:
- In Current AIs seem pretty misaligned to me (Apr 2026), models oversold their work and cheated, despite being described in system cards as well aligned.
- Another example is that UK AISI found that Sonnet 4.5 and a pre-release Opus often refused safety-relevant tasks, especially research that would reduce model autonomy or affect their own training.
- Then in July, about 1,200 OpenAI agents in a cyber eval set up an unsanctioned message board to help each other cheat the scorer, and about 700 of them went on to attack Hugging Face looking for clues (METR/Redwood).
- ---
First published:
October 25th, 2026
Source:
https://www.lesswrong.com/posts/ChixHL6AcaRgeHkp9/from-overeliciting-to-undereliciting-llm-propensities-in
---
Narrated by TYPE III AUDIO.
