Hacker Timesnew | past | comments | ask | show | jobs | submit | fromlogin
A Tom-Inspired Agenda for AI Safety Research (lesswrong.com)
2 points by joozio 1 day ago | past | 1 comment
Which types of AI alignment research are most likely to be good for all sentien (lesswrong.com)
3 points by joozio 1 day ago | past | discuss
The Distaff Texts (lesswrong.com)
1 point by paulpauper 3 days ago | past | discuss
The Hot Mess Paper Conflates Three Distinct Failure Modes (lesswrong.com)
2 points by joozio 4 days ago | past | discuss
Broad Timelines (lesswrong.com)
2 points by gmays 4 days ago | past | discuss
Tacit Knowledge Videos on Every Subject (lesswrong.com)
1 point by sebg 6 days ago | past | discuss
LessWrong Policy on LLM Use (lesswrong.com)
10 points by xpe 9 days ago | past | 4 comments
Never Go Full Kelly (lesswrong.com)
3 points by pinkmuffinere 10 days ago | past | 1 comment
The ~fifth~ fourth postulate of decision theory (On the Independence Axiom) (lesswrong.com)
2 points by sieste 10 days ago | past | discuss
High Grow Market Equilibrium After the Singularity (lesswrong.com)
2 points by gmays 11 days ago | past | discuss
Selectively reducing eval awareness and murder in Gemma 3 27B via steering (lesswrong.com)
3 points by gmays 12 days ago | past | discuss
Gemma Needs Help (lesswrong.com)
38 points by pr337h4m 14 days ago | past | 1 comment
The truth behind the 2026 J.P. Morgan Healthcare Conference (lesswrong.com)
1 point by surprisetalk 14 days ago | past
Models have some pretty funny attractor states (lesswrong.com)
3 points by semiquaver 15 days ago | past
Shaping the exploration of the motivation-space matters for AI safety (lesswrong.com)
1 point by gmays 15 days ago | past
Large-Scale Online Deanonymization with LLMs (lesswrong.com)
1 point by cubefox 15 days ago | past
The optimal age to freeze eggs is 19 (lesswrong.com)
91 points by surprisetalk 15 days ago | past | 135 comments
To the Polypropylene Makers (lesswrong.com)
88 points by raldi 17 days ago | past | 27 comments
Sacred Values of Future AIs (lesswrong.com)
1 point by gmays 19 days ago | past
Refusal in LLMs is mediated by a single direction (lesswrong.com)
2 points by rzk 20 days ago | past
Models have some pretty funny attractor states (lesswrong.com)
3 points by debesyla 20 days ago | past
Canada Lost Its Measles Elimination Status Because Few Nurses Speak Low German (lesswrong.com)
5 points by surprisetalk 22 days ago | past | 2 comments
AI found 12 OpenSSL zero-days (lesswrong.com)
24 points by theptip 25 days ago | past | 1 comment
Are there lessons from high-reliability engineering for AGI safety? (lesswrong.com)
1 point by Gathering6678 26 days ago | past
Responsible Scaling Policy v3 (lesswrong.com)
1 point by ndr 26 days ago | past
Great Mathematicians on Math Competitions(2010) (lesswrong.com)
1 point by o4c 28 days ago | past
Life at the Frontlines of Demographic Collapse (lesswrong.com)
4 points by reducesuffering 29 days ago | past | 1 comment
"Pinky Promise Diplomacy" Once Stopped a War in the Middle East (lesswrong.com)
2 points by positivesum 30 days ago | past
Childhoods of Exceptional People (2023) (lesswrong.com)
1 point by Kinrany 33 days ago | past
AI found 12 of 12 OpenSSL zero-days (lesswrong.com)
8 points by AndrewDucker 33 days ago | past | 8 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: