Dragon God

Oct 16, 2024 | lesswrong.com | Dragon God

Sleeping Beauty volunteers to undergo the following experiment and is told all of the following details: On Sunday she will be put to sleep. Once or twice, during the experiment, Sleeping Beauty will be awakened, interviewed, and put back to sleep with an amnesia-inducing drug that makes her forget that awakening. A fair coin will be tossed to determine which experimental procedure to undertake:If the coin comes up heads, Sleeping Beauty will be awakened and interviewed on Monday only.

Apr 7, 2023 | lesswrong.com | Dragon God

Mar 20, 2023 | lesswrong.com | Cleo Nardo |Bogdan Ionut Cirstea |Dragon God |Yair Halberstadt

Status: Highly-compressed insights about LLMs. Includes exercises. Remark 3 and Remark 15 are the most important and entirely self-contained. Let T be the set of possible tokens in our vocabulary. A language model (LLM) is given by a stochastic function μ:T∗→Δ(T) mapping a prompt (t1…tk) to a predicted token tk+1. By iteratively appending the continuation to the prompt, the language model μ induces a stochastic function ¯μ:T∗→Δ(T∗) mapping a prompt (t1…tk) to (t1…tk+1).

Feb 12, 2023 | lesswrong.com | Rob Bensinger |Dragon God |David Hornbein |Someone YouOnceKnew

How about "hurting a person or deminishing their credibility, or the credibility of their argument, without using a rational argument"? "Hurting a person" still seems too vague to me (sometimes people are "hurt" just because you disagreed with them on a claim of fact), "Diminishing...