درباره این اپیزود
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.
انگلیسی
ایالات متحده آمریکا
رونوشت 🔗
Are you the producer of this podcast?
Add a podcast transcript
Need Audio-to-Text?
Transcribe with Listen411 in Just 60 Seconds
جستجوی اپیزودهای گذشته
اپیزودهای قبلی LessWrong (Curated & Popular) را جستجو کن.
قسمت های دیگر در این پادکست
I’m writing these lines in Alamogordo, New Mexico. I’m about as close as a civilian can get to the site of the Trinity test, the first nuclear bomb detonation in history. I fled here from the San Francisco Bay Area; after two weeks of being back I just couldn’t take it anymore. The fear-greed compl…
This is a weird moment. I have a hunch that we'll look back later and tell ourselves stories in which it seemed obvious where things were going. So I wanted to lay down a little time capsule and register just how confusing everything felt at the time. This is a personal view from the trenches.…
Or if you prefer, "@Claude", "@Opus", "@Astra" @Grok is a popular Twitter/X feature where if you tag Grok in a tweet, Grok will respond in a comment. The stereotypical use case is "@Grok is this true?" But you can also ask things like "How does this comp…
You will agree that for a woman who has fought three duels, all of them kills, indulging in such fears is ludicrous. But what's around the corner now is a duel so big that I don't think I have the guts for it; in Faust's words: Verweile doch, du bist so schoen! Keep it as it is. Don&…
سلب مسئولیت: پادکست و آثار هنری تعبیه شده در این صفحه متعلق به LessWrong است که متعلق به صاحب آن است و به Listen Notes، Inc وابسته یا تایید نشده است.
ویرایش
از کمک شما برای بروز نگهداشتن پایگاهدادههای پادکست سپاسگزاریم
