From overeliciting to undereliciting LLM propensities in just a few months — LessWrong
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…
