RSS

ProgramCrafter

Karma: 309

I want everyone to be able to achieve world they would really like; guess the best way to do that is to help people learn, build one’s strengths, build small-scale and large-scale projects, and also to cooperate.

Any gift must be accepted with gratitude and, if possible, with grace.

As of 2024-12-21, I have signed no contracts I cannot mention exist. I finally got to adding this notice thanks to the one in the-gears-to-ascension’s bio.

Re­view: Dr Stone

ProgramCrafterSep 29, 2024, 10:35 AM
18 points
9 comments4 min readLW link

[Question] Look­ing for in­tu­itions to ex­tend bar­gain­ing notions

ProgramCrafterAug 24, 2024, 5:00 AM
13 points
0 comments1 min readLW link

Mov­ing away from phys­i­cal continuity

ProgramCrafterJul 12, 2024, 5:05 AM
2 points
1 comment1 min readLW link

In­ner Op­ti­miza­tion Mechanisms in Neu­ral Nets

ProgramCrafterMay 12, 2024, 5:52 PM
3 points
1 comment1 min readLW link

User-in­cli­na­tion-guess­ing al­gorithms: reg­is­ter­ing a goal

ProgramCrafterMar 20, 2024, 3:55 PM
2 points
0 comments2 min readLW link

Pro­gramCrafter’s Shortform

ProgramCrafterJul 21, 2023, 5:26 AM
2 points
19 commentsLW link

LLM mis­al­ign­ment can prob­a­bly be found with­out man­ual prompt engineering

ProgramCrafterJul 8, 2023, 2:35 PM
1 point
0 comments1 min readLW link

[Question] Does ob­ject per­ma­nence of simu­lacrum af­fect LLMs’ rea­son­ing?

ProgramCrafterApr 19, 2023, 4:28 PM
1 point
1 comment1 min readLW link

The frozen neutrality

ProgramCrafterApr 1, 2023, 12:58 PM
3 points
0 comments3 min readLW link

Pro­posal on AI eval­u­a­tion: false-proving

ProgramCrafterMar 31, 2023, 12:12 PM
1 point
2 comments1 min readLW link

How AI could workaround goals if rated by people

ProgramCrafterMar 19, 2023, 3:51 PM
1 point
1 comment1 min readLW link