RSS

Skil­lshare: Sleight of Hand

jenn19 Mar 2024 4:25 UTC
5 points
0 comments1 min readLW link

Claude es­ti­mates 30-50% like­li­hood x-risk

amelia19 Mar 2024 2:22 UTC
2 points
0 comments2 min readLW link

[Linkpost] Tran­script of Sam Alt­man’s Lex Frid­man interview

trevor19 Mar 2024 1:46 UTC
18 points
2 comments69 min readLW link
(lexfridman.com)

Ex­per­i­men­ta­tion (Part 7 of “The Sense Of Phys­i­cal Ne­ces­sity”)

LoganStrohl18 Mar 2024 21:25 UTC
29 points
0 comments10 min readLW link

INTERVIEW: Round 2 - StakeOut.AI w/​ Dr. Peter Park

jacobhaimes18 Mar 2024 21:21 UTC
5 points
0 comments1 min readLW link
(into-ai-safety.github.io)

Neu­ro­science and Alignment

Garrett Baker18 Mar 2024 21:09 UTC
33 points
8 comments2 min readLW link

GPT, the mag­i­cal col­lab­o­ra­tion zone, Lex Frid­man and Sam Altman

Bill Benzon18 Mar 2024 20:04 UTC
4 points
0 comments3 min readLW link

It’s Just A …

X O and X O
18 Mar 2024 19:23 UTC
−7 points
1 comment14 min readLW link

Mea­sur­ing Co­her­ence of Poli­cies in Toy Environments

18 Mar 2024 17:59 UTC
45 points
4 comments14 min readLW link

AtP*: An effi­cient and scal­able method for lo­cal­iz­ing LLM be­havi­our to components

18 Mar 2024 17:28 UTC
9 points
0 comments1 min readLW link
(arxiv.org)

Com­mu­nity Notes by X

NicholasKees18 Mar 2024 17:13 UTC
71 points
4 comments7 min readLW link

[Question] Is the Basilisk pre­tend­ing to be hid­den in this simu­la­tion so that it can check what I would do if con­di­tioned by a world with­out the Basilisk?

maybefbi18 Mar 2024 16:05 UTC
−18 points
1 comment1 min readLW link

On Devin

Zvi18 Mar 2024 13:20 UTC
84 points
14 comments11 min readLW link
(thezvi.wordpress.com)

RLLMv10 experiment

MiguelDev18 Mar 2024 8:32 UTC
−3 points
0 comments2 min readLW link

Join the AI Eval­u­a­tion Tasks Bounty Hackathon

Esben Kran18 Mar 2024 8:15 UTC
11 points
0 comments1 min readLW link

5 Physics Problems

18 Mar 2024 8:05 UTC
45 points
0 comments15 min readLW link

In­fer­ring the model di­men­sion of API-pro­tected LLMs

Ege Erdil18 Mar 2024 6:19 UTC
26 points
1 comment4 min readLW link
(arxiv.org)

AI strat­egy given the need for good reflection

owencb18 Mar 2024 0:48 UTC
7 points
0 comments1 min readLW link

XAI re­leases Grok base model

g-w118 Mar 2024 0:47 UTC
7 points
3 comments1 min readLW link
(x.ai)

Chap­ter 9: The Three Powers

SashaWu17 Mar 2024 22:28 UTC
0 points
0 comments4 min readLW link