Eric Ho

[Linkpost] Play with SAEs on Llama 3

• Eric Ho 14 Dec 2023 22:42 UTC

  1 point

  0

  in reply to: Chris_Leong’s comment on: Some for-profit AI al­ign­ment org ideas

  Thanks Chris, I know Brandon there! Appreciate the suggestion

• Eric Ho 14 Dec 2023 19:59 UTC

  1 point

  0

  in reply to: Roman Leventov’s comment on: Some for-profit AI al­ign­ment org ideas

  Yeah I was giving a few examples of ideas there, but agreed that identity and proof of human/​AI are important problems to tackle, and that the topic of filtering out harmful information and sorting through the sea of info can be a big opportunity.

• Eric Ho 14 Dec 2023 19:49 UTC

  1 point

  0

  in reply to: Roman Leventov’s comment on: Some for-profit AI al­ign­ment org ideas

  Yes! That’s a great example

• Eric Ho 14 Dec 2023 19:49 UTC

  2 points

  0

  in reply to: Marius Hobbhahn’s comment on: Some for-profit AI al­ign­ment org ideas

  Thanks Marius, definitely agreed that business model alignment is critical here, and that culture and investors matter a bunch in determining the amount of impact an org has.

• Eric Ho 14 Dec 2023 17:35 UTC

  1 point

  0

  in reply to: Brendon_Wong’s comment on: Some for-profit AI al­ign­ment org ideas

  Responded! And thanks for sharing, will check out those posts. Really enjoyed the first one which I read the other day.

Some for-profit AI al­ign­ment org ideas