Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Notes on Cooperating with Unaligned AIs (greaterwrong.com)
2 points by indigodaddy 89 days ago | past
The Jackpot Age (greaterwrong.com)
3 points by jimsojim 3 months ago | past | 1 comment
Foom and Doom 1: "Brain in a box in a basement" (greaterwrong.com)
7 points by _p2zi 5 months ago | past
Reflections on Neuralese (greaterwrong.com)
17 points by tie-in 6 months ago | past
Playing in the Creek (greaterwrong.com)
1 point by sl-1 7 months ago | past
Ruling Out Lookup Tables (greaterwrong.com)
1 point by paulpauper 9 months ago | past
Gradual Disempowerment, Shell Games and Flinches (greaterwrong.com)
2 points by paulpauper 9 months ago | past
Polytopes (greaterwrong.com)
4 points by paulpauper 10 months ago | past
Thomas C. Schelling's "Strategy of Conflict" (greaterwrong.com)
1 point by paulpauper 10 months ago | past
The Plan − 2024 Update (greaterwrong.com)
1 point by paulpauper 10 months ago | past
A Different Angle on Thinking Balance (greaterwrong.com)
2 points by paulpauper on Nov 8, 2024 | past
The Sun is big, but superintelligences will not spare Earth a little sunlight (greaterwrong.com)
2 points by paulpauper on Nov 8, 2024 | past
Work on Security Instead of Friendliness? – Wei Dai (2012) (greaterwrong.com)
1 point by janandonly on June 17, 2024 | past
Mapping the semantic void: Strange goings-on in GPT embedding spaces (greaterwrong.com)
2 points by DarmokJalad1701 on Dec 19, 2023 | past
OpenAI: Facts from a Weekend (greaterwrong.com)
2 points by hollerith on Nov 20, 2023 | past
How likely is deceptive alignment? (greaterwrong.com)
1 point by behnamoh on May 23, 2023 | past
Advice for High School #2 (greaterwrong.com)
1 point by paulpauper on March 1, 2022 | past
Bad names make you open the box (greaterwrong.com)
2 points by ogennadi on June 9, 2021 | past | 2 comments
Hardware is already ready for the singularity. Algorithms are the only barrier (greaterwrong.com)
3 points by optimalsolver on March 31, 2021 | past
Talented People Frequently Don’t Rise to the Top (greaterwrong.com)
80 points by optimalsolver on March 25, 2021 | past | 61 comments
What I’d Change About Different Philosophy Fields (greaterwrong.com)
1 point by optimalsolver on March 8, 2021 | past
Unconvenient consequences of the logic behind the second law of thermodynamics (greaterwrong.com)
2 points by optimalsolver on March 7, 2021 | past
Fun with 12 OOMs of Compute (greaterwrong.com)
1 point by optimalsolver on March 2, 2021 | past
How my school gamed the stats (greaterwrong.com)
148 points by optimalsolver on Feb 21, 2021 | past | 158 comments
DALL-E does symbol grounding (greaterwrong.com)
2 points by optimalsolver on Jan 19, 2021 | past
Is Stupidity Expanding? Some Hypotheses (greaterwrong.com)
322 points by onemind on Oct 15, 2020 | past | 295 comments
Interpreting GPT: The Logit Lens (greaterwrong.com)
2 points by optimalsolver on Sept 1, 2020 | past | 1 comment
Attention control is critical for increasing/altering motivation (2012) (greaterwrong.com)
3 points by dvaun on July 24, 2020 | past
Noticing the Taste of Lotus (2018) (greaterwrong.com)
1 point by reedwolf on July 19, 2020 | past
Was a PhD necessary to solve outstanding math problems? (greaterwrong.com)
57 points by reedwolf on July 11, 2020 | past | 52 comments

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

Search: