Cost, Not Sacrifice

Joe Rogero20 Nov 2024 21:32 UTC

17 points

2 comments1 min readLW link

(subatomicarticles.com)

[Question] How can we prevent AGI value drift?

Dakara20 Nov 2024 18:19 UTC

16 points

1 comment1 min readLW link

Why I Think All The Species Of Significantly Debated Consciousness Are Conscious And Suffer Intensely

omnizoid20 Nov 2024 16:48 UTC

4 points

2 comments33 min readLW link

Zvi’s Thoughts on His 2nd Round of SFF

Zvi20 Nov 2024 13:40 UTC

73 points

1 comment10 min readLW link

(thezvi.wordpress.com)

A Little Depth Goes a Long Way: the Expressive Power of Log-Depth Transformers

Bogdan Ionut Cirstea20 Nov 2024 11:48 UTC

15 points

0 comments1 min readLW link

(openreview.net)

[Question] What are the good rationality films?

Ben Pace20 Nov 2024 6:04 UTC

64 points

32 comments1 min readLW link

Valence Need Not Be Bounded; Utility Need Not Synthesize

Lorec20 Nov 2024 1:37 UTC

6 points

0 comments6 min readLW link

Value/Utility: A History

Lorec19 Nov 2024 23:01 UTC

9 points

0 comments10 min readLW link

Why Don’t We Just… Shoggoth+Face+Paraphraser?

Daniel Kokotajlo and abramdemski

19 Nov 2024 20:53 UTC

90 points

36 comments14 min readLW link

Every niche event should also be a meetup

DMMF19 Nov 2024 20:47 UTC

16 points

0 comments3 min readLW link

(danfrank.ca)

Root node of my posts

AtillaYasar19 Nov 2024 20:09 UTC

2 points

0 comments3 min readLW link

Intrinsic Power-Seeking: AI Might Seek Power for Power’s Sake

TurnTrout19 Nov 2024 18:36 UTC

37 points

3 comments1 min readLW link

(turntrout.com)

Evolution’s selection target depends on your weighting

tailcalled19 Nov 2024 18:24 UTC

23 points

22 comments1 min readLW link

Visualizing small Attention-only Transformers

WCargo19 Nov 2024 9:37 UTC

3 points

0 comments8 min readLW link

No Electricity in Manchuria

winstonBosan19 Nov 2024 1:11 UTC

20 points

0 comments5 min readLW link

Don’t Dismiss on Epistemics

ggex19 Nov 2024 0:44 UTC

9 points

3 comments2 min readLW link

Training AI agents to solve hard problems could lead to Scheming

Marius Hobbhahn and AlexMeinke

19 Nov 2024 0:10 UTC

58 points

12 comments28 min readLW link

Proactive ‘If-Then’ Safety Cases

Nathan Helm-Burger18 Nov 2024 21:16 UTC

8 points

0 comments4 min readLW link

[Question] Will Orion/Gemini 2/Llama-4 outperform o1

LuigiPagani18 Nov 2024 21:15 UTC

1 point

3 comments1 min readLW link

How to use bright light to improve your life.

Nat Martin18 Nov 2024 19:32 UTC

33 points

5 comments10 min readLW link