EuanMcLean

What mis­takes has the AI safety move­ment made?

What should AI safety be try­ing to achieve?

What will the first hu­man-level AI look like, and how might things go wrong?

Big Pic­ture AI Safety: Introduction

2023 Align­ment Re­search Up­dates from FAR AI

What’s new at FAR AI

Even Su­per­hu­man Go AIs Have Sur­pris­ing Failure Modes

AI Safety in a World of Vuln­er­a­ble Ma­chine Learn­ing Systems

• 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!

De­con­fus­ing Lan­dauer’s Principle