EuanMcLean

• EuanMcLean 1 Nov 2024 12:11 UTC

  1 point

  0

  in reply to: Garrett Baker’s comment on: Search­ing for phe­nom­e­nal con­scious­ness in LLMs: Per­cep­tual re­al­ity mon­i­tor­ing and in­tro­spec­tive confidence

  Thanks for the feedback Garrett.

  This was intended to be more of a technical report than a blog post, meaning I wanted to keep the discussion reasonably rigorous/​thorough. Which always comes with the downside of it being a slog to read, so apologies for that!

  I’ll write a shortened version if I find the time!

• EuanMcLean 1 Nov 2024 12:08 UTC

  1 point

  0

  in reply to: James Chua’s comment on: Search­ing for phe­nom­e­nal con­scious­ness in LLMs: Per­cep­tual re­al­ity mon­i­tor­ing and in­tro­spec­tive confidence

  Thanks James!

  One failure mode is that the modification makes the model very dumb in all instances.

  Yea, good point. Perhaps an extra condition we’d need to include is that the “difficulty of meta-level questions” should be the same before and after the modification—e.g. - the distribution over stuff it’s good at and stuff its bad at should be just as complex (not just good at everything or bad at everything) before and after

• EuanMcLean 1 Nov 2024 12:00 UTC

  1 point

  0

  in reply to: Felix J Binder’s comment on: Search­ing for phe­nom­e­nal con­scious­ness in LLMs: Per­cep­tual re­al­ity mon­i­tor­ing and in­tro­spec­tive confidence

  Thanks Felix!

  This is indeed a cool and surprising result. I think it strengthens the introspection interpretation, but without a requirement to make a judgement of the reliability of some internal signal (right?), it doesn’t directly address the question of whether there is a discriminator in there.

• EuanMcLean 29 May 2024 11:52 UTC

  1 point

  0

  in reply to: Joseph Miller’s comment on: What will the first hu­man-level AI look like, and how might things go wrong?

  Interesting question! I’m afraid I didn’t probe the cruxes of those who don’t expect hard takeoff. But my guess is that you’re right—no hard takeoff ~= the most transformative effects happen before recursive self-improvement

• EuanMcLean 23 Jun 2022 19:27 UTC

  3 points

  in reply to: philh’s comment on: De­con­fus­ing Lan­dauer’s Principle

  Yea, I think you’re hitting on a weird duality between setting and erasing here. I think I agree that setting is more fundamental than erasing. I suppose when talking about energy expenditure of computation, each set bit must be erased in the long run, so they’re interchangeable in that sense.

• EuanMcLean 6 Jun 2022 19:07 UTC

  1 point

  in reply to: kave’s comment on: De­con­fus­ing Lan­dauer’s Principle

  Sorry for the delay. As both you and TheMcDouglas have mentioned; yea, this relies on $H(C|X) = 0$. The way I’ve worded it above is somewhere between misleading and wrong, have modified. Thanks for pointing this out!

• EuanMcLean 29 May 2022 11:53 UTC

  1 point

  in reply to: Thomas Kehrenberg’s comment on: De­con­fus­ing Lan­dauer’s Principle

  Fixed, thanks!

• EuanMcLean 28 May 2022 11:29 UTC

  3 points

  in reply to: Steven Byrnes’s comment on: De­con­fus­ing Lan­dauer’s Principle

  Thanks for the comment, this is indeed an important component! I’ve added a couple of sentences pointing in this direction.

• EuanMcLean 28 May 2022 9:46 UTC

  1 point

  in reply to: Adrià Garriga-alonso’s comment on: De­con­fus­ing Lan­dauer’s Principle

  fixed, thanks!