jylin04

• jylin04 3 Oct 2022 10:29 UTC

  7 points

  0 ∶ 0

  on: Win­ners of the EA Crit­i­cism and Red Team­ing Contest

  Thanks, that’s a good point. Just posted it here: https://​​www.lesswrong.com/​​posts/​​TMHWfRE7zZkzgFDSo/​​a-review-of-the-bio-anchors-report

• jylin04 1 Oct 2022 15:21 UTC

  5 points

  0 ∶ 0

  in reply to: elifland’s comment on: Win­ners of the EA Crit­i­cism and Red Team­ing Contest

  Yes, it’s mentioned on page 19 of part 4 (as point 1, and my main concern is with point 2b).

• jylin04 1 Oct 2022 9:53 UTC

  5 points

  0 ∶ 0

  in reply to: Charles He’s comment on: Win­ners of the EA Crit­i­cism and Red Team­ing Contest

  Regarding the questions about feedforward networks, a really short answer is that regression is a very limited form of inference-time computation that e.g. rules out using memory. (Of course, as you point out, this doesn’t apply to other 2020 algorithms beyond MLPs.) Sorry about the lack of clarity—I didn’t want to take up too much space in this piece going into the details of the linked papers, but hopefully I’ll be able to do a better job explaining it in a review of those papers that I’ll post on LW/​AF next week.

  (I also want to reply to your top-level comments about the evolutionary anchor, but am a bit short on time to do it right now (since for those questions I don’t have cached technical answers and will have to remind myself about the context). But I’ll definitely get to it next week.)

• jylin04 1 Oct 2022 9:48 UTC

  12 points

  2 ∶ 0

  in reply to: Charles He’s comment on: Win­ners of the EA Crit­i­cism and Red Team­ing Contest

  Hi Charles, thanks for all the comments! I’ll reply to this one first since it seems like the biggest crux. I completely agree with you that feedforward NNs != RNN/​LSTM… and that I haven’t given a crisp argument that the latter can’t scale to TAI. But I don’t think I claim to in the piece! All I wanted to do here was to (1) push back against the claim that the UAT for feedforward networks provides positive evidence that DL->TAI, and (2) give an example of a strategy that could be used to argue in a more principled way that other architectures won’t scale up to certain capabilities, if one is able to derive effective theories for them as was done for MLPs by Roberts et al. (I think it would be really interesting to show this for other architectures and I’d like to think more about it in the future.)

• jylin04 1 Oct 2022 9:44 UTC

  31 points

  0 ∶ 0

  in reply to: aogara’s comment on: Win­ners of the EA Crit­i­cism and Red Team­ing Contest

  Hi, I’m the author of the piece. Thanks for the kind comment! I planned to share it on LW/​AF after finishing a companion piece on the work by Roberts et al. that I use in the technical section, and I fell a bit behind schedule on writing the second piece, but I’ll put both on LW/​AF next week.