RSS

Black Box Biology

GeneSmith29 Nov 2023 2:27 UTC
45 points
16 comments2 min readLW link

Spaced rep­e­ti­tion for teach­ing two-year olds how to read (In­ter­view)

Chipmonk26 Nov 2023 16:52 UTC
44 points
7 comments5 min readLW link
(chipmonk.substack.com)

ChatGPT 4 solved all the gotcha prob­lems I posed that tripped ChatGPT 3.5

VipulNaik29 Nov 2023 18:11 UTC
19 points
2 comments14 min readLW link

How to Con­trol an LLM’s Be­hav­ior (why my P(DOOM) went down)

RogerDearnaley28 Nov 2023 19:56 UTC
46 points
22 comments10 min readLW link

Wikipe­dia is not so great, and what can be done about it.

less_than_226 Nov 2023 19:13 UTC
−2 points
27 comments16 min readLW link
(forum.effectivealtruism.org)

De­cep­tion Chess: Game #2

Zane29 Nov 2023 2:43 UTC
23 points
13 comments2 min readLW link

The 101 Space You Will Always Have With You

Screwtape29 Nov 2023 4:56 UTC
90 points
7 comments6 min readLW link

Game The­ory with­out Argmax [Part 1]

Cleo Nardo11 Nov 2023 15:59 UTC
49 points
11 comments19 min readLW link

An­thropic Fall 2023 De­bate Progress Update

Ansh Radhakrishnan28 Nov 2023 5:37 UTC
52 points
3 comments12 min readLW link

AI Timelines

10 Nov 2023 5:28 UTC
224 points
69 comments51 min readLW link

[Question] Thoughts on tele­trans­porta­tion with copies?

titotal29 Nov 2023 12:56 UTC
11 points
10 comments1 min readLW link

Abil­ity to solve long-hori­zon tasks cor­re­lates with want­ing things in the be­hav­iorist sense

So8res24 Nov 2023 17:37 UTC
198 points
71 comments5 min readLW link

Paper: “FDT in an evolu­tion­ary en­vi­ron­ment”

the gears to ascension27 Nov 2023 5:27 UTC
26 points
40 comments1 min readLW link
(arxiv.org)

Value sys­tem­ati­za­tion: how val­ues be­come co­her­ent (and mis­al­igned)

Richard_Ngo27 Oct 2023 19:06 UTC
87 points
35 comments13 min readLW link

[Question] Could Ger­many have won World War I with high prob­a­bil­ity given the benefit of hind­sight?

Roko27 Nov 2023 22:52 UTC
10 points
16 comments1 min readLW link

A free to en­ter, 240 char­ac­ter, open-source iter­ated pris­oner’s dilemma tournament

Isaac King9 Nov 2023 8:24 UTC
54 points
16 comments1 min readLW link
(manifold.markets)

Shal­low re­view of live agen­das in al­ign­ment & safety

27 Nov 2023 11:10 UTC
212 points
52 comments29 min readLW link

[Question] How can I use AI with­out in­creas­ing AI-risk?

Yoav Ravid28 Nov 2023 10:05 UTC
18 points
6 comments1 min readLW link

One Day Sooner

Screwtape2 Nov 2023 19:00 UTC
91 points
5 comments8 min readLW link

[Question] What works for ADHD and/​or re­lated things?

TeaTieAndHat2 Aug 2023 18:37 UTC
6 points
13 comments1 min readLW link