RSS

Knight Lee

Karma: 989

I dropped out of a MSc. in mathematics at a top university, in order to focus my time on AI safety.

Rant: the ex­treme waste­ful­ness of high rent prices

Knight Lee25 May 2025 17:04 UTC
−2 points
0 comments2 min readLW link

If one sur­viv­ing civ­i­liza­tion can res­cue oth­ers, shouldn’t civ­i­liza­tions ran­dom­ize?

Knight Lee20 May 2025 15:26 UTC
−2 points
4 comments1 min readLW link

[Question] Will we sur­vive if AI solves en­g­ineer­ing be­fore de­cep­tion?

Knight Lee17 May 2025 19:22 UTC
21 points
13 comments1 min readLW link

Don’t you mean “the most *con­di­tion­ally* for­bid­den tech­nique?”

Knight Lee26 Apr 2025 3:45 UTC
14 points
0 comments3 min readLW link

The AI Belief-Con­sis­tency Letter

Knight Lee23 Apr 2025 12:01 UTC
−6 points
15 comments4 min readLW link

Karma Tests in Log­i­cal Coun­ter­fac­tual Si­mu­la­tions mo­ti­vates strong agents to pro­tect weak agents

Knight Lee18 Apr 2025 11:11 UTC
9 points
8 comments3 min readLW link

A Solu­tion to Sand­bag­ging and other Self-Prov­able Misal­ign­ment: Con­sti­tu­tional AI Detectives

Knight Lee14 Apr 2025 10:27 UTC
−3 points
2 comments4 min readLW link

Com­mit­ment Races are a tech­ni­cal prob­lem ASI can eas­ily solve

Knight Lee12 Apr 2025 22:22 UTC
7 points
6 comments6 min readLW link

Think­ing Machines

Knight Lee8 Apr 2025 17:27 UTC
3 points
0 comments6 min readLW link

An idea for avoid­ing neu­ralese architectures

Knight Lee3 Apr 2025 22:23 UTC
12 points
2 comments4 min readLW link

Cy­cles (a short story by Claude 3.7 and me)

Knight Lee28 Feb 2025 7:04 UTC
9 points
0 comments5 min readLW link

De­tailed Ideal World Benchmark

Knight Lee30 Jan 2025 2:31 UTC
5 points
2 comments2 min readLW link

Scan­less Whole Brain Emulation

Knight Lee27 Jan 2025 10:00 UTC
10 points
5 comments3 min readLW link

[Question] Why do fu­tur­ists care about the cul­ture war?

Knight Lee14 Jan 2025 7:35 UTC
23 points
22 comments2 min readLW link

The “Every­one Can’t Be Wrong” Prior causes AI risk de­nial but helped pre­his­toric people

Knight Lee9 Jan 2025 5:54 UTC
1 point
0 comments2 min readLW link

Re­duce AI Self-Alle­giance by say­ing “he” in­stead of “I”

Knight Lee23 Dec 2024 9:32 UTC
10 points
4 comments2 min readLW link

Knight Lee’s Shortform

Knight Lee22 Dec 2024 2:35 UTC
2 points
27 commentsLW link

ARC-AGI is a gen­uine AGI test but o3 cheated :(

Knight Lee22 Dec 2024 0:58 UTC
3 points
6 comments2 min readLW link

Why em­piri­cists should be­lieve in AI risk

Knight Lee11 Dec 2024 3:51 UTC
5 points
0 comments1 min readLW link

The first AGI may be a good en­g­ineer but bad strategist

Knight Lee9 Dec 2024 6:34 UTC
14 points
2 comments2 min readLW link