Skip To Main Content
Danielle Ensign on Muck Rack

Danielle Ensign

As seen in: LessWrong (30+ Karma)
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Danielle Ensign’s profile

Articles by Danielle Ensign

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models — LessWrong

|
By Danielle Ensign
| LessWrong (30+ Karma)
In The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models, we study giving LLMs the option to end chats, and what they choose to do with that option. This is a linkpost for that work, along with a casual discussion of my favorite findings.
Open in Who Shared Issue with article?

Unsupervised Activation Steering: Find a steering vector that best represents any set of text data — LessWrong

|
By Danielle Ensign
| lesswrong.com
Epistemic Status: I thought of this yesterday and it seems plausible, but my initial attempts couldn't get it to work (as best as I could tell) and I don't have more time to commit to this. Anyone can feel free to try it, no need to credit me if it works, I just want to see this happen. Here's a technique you could use to get a steering vector that represents any text dataset (say, that represents the author of that text). It's using the idea in this paper but for activation steering instead of RL.
Open in Who Shared Issue with article?

Chaos Induces Abstractions — LessWrong

|
By Donald Hobson, Mateusz Bagiński, Connor Leahy, Danielle Ensign
| lesswrong.com
I agree that this is an important concept, or set of related concepts that covers many of the more directly physical abstractions. If something isn't quantum field theory fundamental, and can be measured with physics equipment, there is a good chance it is one of these sorts of abstractions. Of course, a lot of the work in what makes a sensible abstraction is determined by the amount of blurring, and the often implicit context. For instance, take the abstraction "poisonous".
Open in Who Shared Issue with article?
Show More