Vivek Hebbar

Jun 23, 2024 | lesswrong.com | Vivek Hebbar

Sometimes people talk about two AIs being “the same” or “different” AIs. We think the intuitive binary of “same vs. different” conflates several concepts which are often better to disambiguate. In this post, we spell out some of these distinctions. We don’t think anything here is particularly novel; we wrote this post because we think it’s probably mildly helpful for people to think this through, and because Buck fairly often wants to reference it.

Sep 28, 2023 | blog.csdn.net | Vivek Hebbar

(not an original, only classified as one to avoid cramming reference links) paper: https://owainevans.github.io/reversal_curse.pdf blog with interactions with the authors: Paper: LLMs trained on “A is B” fail to learn “B is A” — LessWrong This is a linkpost for https://owainevans.github.io/reversal_curse.pdf This post is the copy of the introduction of this paper on the Reversal Curse.

Apr 27, 2023 | alignmentforum.org | Steve Byrnes |Steven Byrnes |Vivek Hebbar |David Johnston

(in the form of an FAQ)A: As background, I think it’s obvious that there will eventually be “transformative AI” (TAI) that would radically change the world. I’m interested in what this TAI will eventually look like algorithmically. Let’s list some possibilities:A “Large Language Model (LLM) plateau-ist” would be defined as someone who thinks that categories (A-B), and usually also (C), will plateau in capabilities before reaching TAI levels. I am an LLM plateau-ist myself.