davidad

Karma: 2,095

Programme Director at UK Advanced Research + Invention Agency focusing on safe transformative AI; formerly Protocol Labs, FHI/Oxford, Harvard Biophysics, MIT Mathematics And Computation.

What does davidad want from «boundaries»?

Chipmonk and davidad

6 Feb 2024 17:45 UTC

44 points

1 comment5 min readLW link

Does davidad’s uploading moonshot work?

jacobjacob, lisathiergart, Anders_Sandberg, davidad and Arenamontanus

3 Nov 2023 2:21 UTC

146 points

35 comments25 min readLW link

A list of core AI safety problems and how I hope to solve them

davidad26 Aug 2023 15:12 UTC

165 points

29 comments5 min readLW link

Compute Thresholds: proposed rules to mitigate risk of a “lab leak” accident during AI training runs

davidad22 Jul 2023 18:09 UTC

80 points

2 comments2 min readLW link

An Open Agency Architecture for Safe Transformative AI

davidad20 Dec 2022 13:04 UTC

79 points

22 comments4 min readLW link

AI Neorealism: a threat model & success criterion for existential safety

davidad15 Dec 2022 13:42 UTC

67 points

1 comment3 min readLW link

Side-channels: input versus output

davidad12 Dec 2022 12:32 UTC

44 points

16 comments2 min readLW link

Reframing inner alignment

davidad11 Dec 2022 13:53 UTC

53 points

13 comments4 min readLW link

You can still fetch the coffee today if you’re dead tomorrow

davidad9 Dec 2022 14:06 UTC

85 points

19 comments5 min readLW link

Cryptoepistemology

davidad24 Feb 2022 20:34 UTC

30 points

3 comments2 min readLW link

The Promise and Peril of Finite Sets

davidad10 Dec 2021 12:29 UTC

42 points

4 comments6 min readLW link

davidad’s Shortform

davidad9 Dec 2021 18:16 UTC

4 points

13 comments1 min readLW link

Why I Moved from AI to Neuroscience, or: Uploading Worms

davidad13 Apr 2012 7:10 UTC

67 points

58 comments1 min readLW link