RSS

PashaKamyshev

Karma: 17

Uploads are Impossible

PashaKamyshev12 May 2023 8:03 UTC
−5 points
37 comments8 min readLW link

Value Learn­ing – Towards Re­solv­ing Con­fu­sion

PashaKamyshev24 Apr 2023 6:43 UTC
4 points
0 comments18 min readLW link

An AI Real­ist Man­i­festo: Nei­ther Doomer nor Foomer, but a third more rea­son­able thing

PashaKamyshev10 Apr 2023 0:11 UTC
16 points
13 comments8 min readLW link

What does it mean for an LLM such as GPT to be al­igned /​ good /​ pos­i­tive im­pact?

PashaKamyshev20 Mar 2023 9:21 UTC
4 points
3 comments10 min readLW link

AI as a Civ­i­liza­tional Risk Part 6/​6: What can be done

PashaKamyshev3 Nov 2022 19:48 UTC
2 points
4 comments4 min readLW link

AI as a Civ­i­liza­tional Risk Part 5/​6: Re­la­tion­ship be­tween C-risk and X-risk

PashaKamyshev3 Nov 2022 2:19 UTC
2 points
0 comments7 min readLW link

AI as a Civ­i­liza­tional Risk Part 4/​6: Bioweapons and Philos­o­phy of Modification

PashaKamyshev1 Nov 2022 20:50 UTC
7 points
1 comment8 min readLW link

AI as a Civ­i­liza­tional Risk Part 3/​6: Anti-econ­omy and Sig­nal Pollution

PashaKamyshev31 Oct 2022 17:03 UTC
7 points
4 comments14 min readLW link

AI as a Civ­i­liza­tional Risk Part 2/​6: Be­hav­ioral Modification

PashaKamyshev30 Oct 2022 16:57 UTC
9 points
0 comments10 min readLW link

AI as a Civ­i­liza­tional Risk Part 1/​6: His­tor­i­cal Priors

PashaKamyshev29 Oct 2022 21:59 UTC
2 points
2 comments7 min readLW link