Cleo Nardo

Karma: 2,270

DMs open.

How should DeepMind’s Chinchilla revise our AI forecasts?

Cleo Nardo15 Sep 2022 17:54 UTC

35 points

12 comments13 min readLW link

Is GPT-N bounded by human capabilities? No.

Cleo Nardo17 Oct 2022 23:26 UTC

48 points

8 comments2 min readLW link

K-types vs T-types — what priors do you have?

Cleo Nardo3 Nov 2022 11:29 UTC

71 points

25 comments7 min readLW link

[Question] EA (& AI Safety) has overestimated its projected funding — which decisions must be revised?

Cleo Nardo11 Nov 2022 13:50 UTC

22 points

7 comments1 min readLW link

(forum.effectivealtruism.org)

Human-level Full-Press Diplomacy (some bare facts).

Cleo Nardo22 Nov 2022 20:59 UTC

50 points

7 comments3 min readLW link

When AI solves a game, focus on the game’s mechanics, not its theme.

Cleo Nardo23 Nov 2022 19:16 UTC

82 points

7 comments2 min readLW link

Against “Classic Style”

Cleo Nardo23 Nov 2022 22:10 UTC

67 points

30 comments4 min readLW link

MIRI’s “Death with Dignity” in 60 seconds.

Cleo Nardo6 Dec 2022 17:18 UTC

55 points

4 comments1 min readLW link

Prosaic misalignment from the Solomonoff Predictor

Cleo Nardo9 Dec 2022 17:53 UTC

40 points

2 comments5 min readLW link

Towards Hodge-podge Alignment

Cleo Nardo19 Dec 2022 20:12 UTC

91 points

30 comments9 min readLW link

What can thought-experiments do?

Cleo Nardo17 Jan 2023 0:35 UTC

16 points

3 comments5 min readLW link

The Waluigi Effect (mega-post)

Cleo Nardo3 Mar 2023 3:22 UTC

618 points

188 comments16 min readLW link

Want to predict/explain/control the output of GPT-4? Then learn about the world, not about transformers.

Cleo Nardo16 Mar 2023 3:08 UTC

105 points

26 comments5 min readLW link

The algorithm isn’t doing X, it’s just doing Y.

Cleo Nardo16 Mar 2023 23:28 UTC

53 points

43 comments5 min readLW link

Remarks 1–18 on GPT (compressed)

Cleo Nardo20 Mar 2023 22:27 UTC

146 points

35 comments31 min readLW link

Wittgenstein and ML — parameters vs architecture

Cleo Nardo24 Mar 2023 4:54 UTC

37 points

8 comments5 min readLW link

The 0.2 OOMs/year target

Cleo Nardo30 Mar 2023 18:15 UTC

84 points

24 comments5 min readLW link

AI Summer Harvest

Cleo Nardo4 Apr 2023 3:35 UTC

130 points

10 comments1 min readLW link

Excessive AI growth-rate yields little socio-economic benefit.

Cleo Nardo4 Apr 2023 19:13 UTC

27 points

22 comments4 min readLW link

List of requests for an AI slowdown/halt.

Cleo Nardo14 Apr 2023 23:55 UTC

46 points

6 comments1 min readLW link