Peter Berggren

Karma: 263

MIT senior majoring in computer science, economics, and data science and double minoring in mathematics and philosophy. Interested in AI safety across a wide range of domains. Blog at

nonmailableliveanimals.substack.com

Why We Need More Shovel-Ready AI Notkilleveryoneism Megaproject Proposals

Peter Berggren20 Jan 2025 22:38 UTC

36 points

1 comment6 min readLW link

A proposal for iterated interpretability with known-interpretable narrow AIs

Peter Berggren11 Jan 2025 14:43 UTC

6 points

0 comments2 min readLW link

Read The Sequences As If They Were Written Today

Peter Berggren2 Jan 2025 2:51 UTC

60 points

7 comments4 min readLW link

A few questions about recent developments in EA

Peter Berggren23 Nov 2024 2:36 UTC

24 points

12 comments2 min readLW link

How do you actually obtain and report a likelihood function for scientific research?

Peter Berggren11 Feb 2024 17:42 UTC

55 points

4 comments1 min readLW link

BOUNTY AVAILABLE: AI ethicists, what are your object-level arguments against AI notkilleveryoneism?

Peter Berggren6 Jul 2023 17:32 UTC

18 points

6 comments2 min readLW link

Peter Berggren

Why We Need More Shovel-Ready AI Notkil­lev­ery­oneism Me­gapro­ject Proposals

A pro­posal for iter­ated in­ter­pretabil­ity with known-in­ter­pretable nar­row AIs

Read The Se­quences As If They Were Writ­ten Today

A few ques­tions about re­cent de­vel­op­ments in EA

How do you ac­tu­ally ob­tain and re­port a like­li­hood func­tion for sci­en­tific re­search?