nostalgebraist

Karma: 4,488

Same person as nostalgebraist2point0, but now I have my account back.

Elsewhere:

When does rationality-as-search have nontrivial implications?

nostalgebraist4 Nov 2018 22:42 UTC

66 points

11 comments3 min readLW link

“embedded self-justification,” or something like that

nostalgebraist3 Nov 2019 3:20 UTC

37 points

14 comments5 min readLW link

(nostalgebraist.tumblr.com)

human psycholinguists: a critical appraisal

nostalgebraist31 Dec 2019 0:20 UTC

180 points

59 comments16 min readLW link 2 reviews

(nostalgebraist.tumblr.com)

mind viruses about body viruses

nostalgebraist28 Mar 2020 4:20 UTC

52 points

12 comments10 min readLW link

(nostalgebraist.tumblr.com)

covid-19 notes, 4/19/20

nostalgebraist20 Apr 2020 5:30 UTC

29 points

1 comment9 min readLW link

(nostalgebraist.tumblr.com)

GPT-3: a disappointing paper

nostalgebraist29 May 2020 19:06 UTC

65 points

43 comments8 min readLW link 1 review

[Question] Why is pseudo-alignment “worse” than other ways ML can fail to generalize?

nostalgebraist18 Jul 2020 22:54 UTC

45 points

9 comments2 min readLW link

[updated] how does gpt2′s training corpus capture internet discussion? not well

nostalgebraist27 Jul 2020 22:30 UTC

25 points

3 comments2 min readLW link

(nostalgebraist.tumblr.com)

is gpt-3 few-shot ready for real applications?

nostalgebraist3 Aug 2020 19:50 UTC

31 points

5 comments9 min readLW link

(nostalgebraist.tumblr.com)

interpreting GPT: the logit lens

nostalgebraist31 Aug 2020 2:47 UTC

204 points

34 comments11 min readLW link

on “learning to summarize”

nostalgebraist12 Sep 2020 3:20 UTC

25 points

13 comments8 min readLW link

(nostalgebraist.tumblr.com)

the scaling “inconsistency”: openAI’s new insight

nostalgebraist7 Nov 2020 7:40 UTC

148 points

14 comments9 min readLW link

(nostalgebraist.tumblr.com)

larger language models may disappoint you [or, an eternally unfinished draft]

nostalgebraist26 Nov 2021 23:08 UTC

254 points

31 comments31 min readLW link 2 reviews

[Link] Training Compute-Optimal Large Language Models

nostalgebraist31 Mar 2022 18:01 UTC

51 points

23 comments1 min readLW link

(arxiv.org)

dalle2 comments

nostalgebraist26 Apr 2022 5:30 UTC

183 points

14 comments13 min readLW link

(nostalgebraist.tumblr.com)

autonomy: the missing AGI ingredient?

nostalgebraist25 May 2022 0:33 UTC

64 points

12 comments6 min readLW link

[Question] why assume AGIs will optimize for fixed goals?

nostalgebraist10 Jun 2022 1:28 UTC

143 points

55 comments4 min readLW link 2 reviews

wrapper-minds are the enemy

nostalgebraist17 Jun 2022 1:58 UTC

104 points

41 comments8 min readLW link

chinchilla’s wild implications

nostalgebraist31 Jul 2022 1:18 UTC

410 points

128 comments10 min readLW link 1 review

OpenAI API base models are not sycophantic, at any size

nostalgebraist29 Aug 2023 0:58 UTC

178 points

19 comments2 min readLW link

(colab.research.google.com)