RSS

Davidmanheim

Karma: 1,170
Page 1

Diver­gence on Ev­i­dence Due to Differ­ing Pri­ors—A Poli­ti­cal Case Study

Davidmanheim
16 Sep 2019 11:01 UTC
27 points
3 comments3 min readLW link

Hack­able Re­wards as a Safety Valve?

Davidmanheim
10 Sep 2019 10:33 UTC
18 points
17 comments1 min readLW link

[Question] What Pro­gram­ming Lan­guage Char­ac­ter­is­tics Would Allow Prov­ably Safe AI?

Davidmanheim
28 Aug 2019 10:46 UTC
5 points
10 comments1 min readLW link

Mesa-Op­ti­miz­ers and Over-op­ti­miza­tion Failure (Op­ti­miz­ing and Good­hart Effects, Clar­ify­ing Thoughts—Part 4)

Davidmanheim
12 Aug 2019 8:07 UTC
17 points
3 comments4 min readLW link