Michael Tontchev

Karma: 56

[New, A-Z in­tro to AI risk]: A gen­tle in­tro­duc­tion to why AI *might* end the hu­man race

Michael Tontchev1 Jun 2023 23:12 UTC
2 points
0 comments1 min readLW link

A rough model for P(AI doom)

Michael Tontchev31 May 2023 8:58 UTC
0 points
1 comment2 min readLW link

Align­ment solu­tions for weak AI don’t (nec­es­sar­ily) scale to strong AI

Michael Tontchev25 May 2023 8:26 UTC
6 points
0 comments5 min readLW link

Unal­igned sta­ble loops emerge at scale

Michael Tontchev6 Apr 2023 2:15 UTC
9 points
8 comments4 min readLW link

ChatGPT’s “fuzzy al­ign­ment” isn’t ev­i­dence of AGI al­ign­ment: the ba­nana test

Michael Tontchev23 Mar 2023 7:12 UTC
23 points
6 comments4 min readLW link

A method for em­piri­cal back-test­ing of AI’s abil­ity to self-improve

Michael Tontchev21 Mar 2023 20:24 UTC
3 points
0 comments2 min readLW link


Michael Tontchev14 Mar 2023 22:03 UTC
7 points
0 comments11 min readLW link