RSS

SAE Prob­ing: What is it good for? Ab­solutely some­thing!

1 Nov 2024 19:23 UTC
18 points
0 comments11 min readLW link

[Question] Set The­ory Mul­ti­verse vs Math­e­mat­i­cal Truth—Philo­soph­i­cal Discussion

Wenitte Apiou1 Nov 2024 18:56 UTC
4 points
4 comments1 min readLW link

Ed­u­ca­tional CAI: Align­ing a Lan­guage Model with Ped­a­gog­i­cal Theories

Bharath Puranam1 Nov 2024 18:55 UTC
1 point
0 comments13 min readLW link

Pre­dic­tion mar­kets and Taxes

Edmund Nelson1 Nov 2024 17:39 UTC
7 points
7 comments1 min readLW link

Den­tistry, Oral Sur­geons, and the Ineffi­ciency of Small Markets

GeneSmith1 Nov 2024 17:26 UTC
45 points
8 comments5 min readLW link

Com­plete Feedback

abramdemski1 Nov 2024 16:58 UTC
20 points
0 comments3 min readLW link

Lev­ers for Biolog­i­cal Progress—A Re­sponse to “Machines of Lov­ing Grace”

Niko_McCarty1 Nov 2024 16:35 UTC
3 points
0 comments20 min readLW link
(www.asimov.press)

[Question] When en­gag­ing with a large amount of re­sources dur­ing a liter­a­ture re­view, how do you pre­vent your­self from be­com­ing over­whelmed?

corruptedCatapillar1 Nov 2024 7:29 UTC
25 points
2 comments3 min readLW link

(draft) Cy­borg soft­ware should be open (?)

AtillaYasar1 Nov 2024 7:24 UTC
0 points
4 comments3 min readLW link

Another UFO Bet

codyz1 Nov 2024 1:55 UTC
6 points
3 comments1 min readLW link

Jar­gonBot Beta Test

Raemon1 Nov 2024 1:05 UTC
53 points
36 comments6 min readLW link

GPT-4o Guardrails Gone: Data Poi­son­ing & Jailbreak-Tuning

1 Nov 2024 0:10 UTC
12 points
0 comments6 min readLW link
(far.ai)

The sling­shot helps with learning

Wilson Wu31 Oct 2024 23:18 UTC
30 points
0 comments8 min readLW link

Toward Safety Case In­spired Ba­sic Research

31 Oct 2024 23:06 UTC
24 points
2 comments13 min readLW link

Spooky Recom­men­da­tion Sys­tem Scaling

phdead31 Oct 2024 22:00 UTC
10 points
0 comments4 min readLW link

‘Meta’, ‘mesa’, and mountains

Lorec31 Oct 2024 17:25 UTC
0 points
0 comments3 min readLW link

Toward Safety Cases For AI Scheming

31 Oct 2024 17:20 UTC
53 points
1 comment2 min readLW link

The Com­pendium, A full ar­gu­ment about ex­tinc­tion risk from AGI

31 Oct 2024 12:01 UTC
150 points
21 comments2 min readLW link
(www.thecompendium.ai)

Some Pre­limi­nary Notes on the Promise of a Wis­dom Explosion

Chris_Leong31 Oct 2024 9:21 UTC
2 points
0 comments1 min readLW link
(aiimpacts.org)

What TMS is like

Sable31 Oct 2024 0:44 UTC
167 points
13 comments6 min readLW link
(affablyevil.substack.com)