Adrià Moret

• Adrià Moret 6 Mar 2026 13:13 UTC

  3 points

  1 ∶ 0

  in reply to: Vasco Grilo🔸’s comment on: Digi­tal Con­scious­ness Model Re­sults and Key Takeaways

  I think this would be a really good idea. As you hint at, it could allow people to better calibrate re the importance/​significance of evidence, which is weaker than in the case of human adults. I also expect a model that gives more plausible results for newborns/​infants to also give more plausible results for chickens.

Digi­tal Con­scious­ness Model Re­sults and Key Takeaways

AI Align­ment: The Case for In­clud­ing Animals

AI Welfare Risks

• Adrià Moret 3 Jul 2024 8:21 UTC

  3 points

  0 ∶ 0

  in reply to: Lucius Caviola’s comment on: How do AI welfare and AI safety in­ter­act?

  Perfect!

  It’s more or less similar. I do not focus that much on the moral dubiousness of “happy servants”. Instead, I try to show that standard alignment methods or preventing near-future AIs with moral patienthood from taking actions they are trying to take, causes net harm to the AIs according to desire satisfactionism, hedonism and objective list theories.

• Adrià Moret 2 Jul 2024 16:25 UTC

  1 point

  0 ∶ 0

  Error

  The value
    NIL
  is not of type
    SIMPLE-STRING
  when binding #:USER-ID162

• Adrià Moret 1 Jul 2024 23:27 UTC

  16 points

  0 ∶ 0

  on: How do AI welfare and AI safety in­ter­act?

  It’s great to see this topic being discussed. I am currently writing the first (albeit significantly developed) draft of an academic paper on this. I argue that there is a conflict between AI safety and AI welfare concerns. This is so basically because (to reduce catastrophic risk) AI safety recommends implementing various kinds of control measures to near-future AI systems which are (in expectation) net-harmful for AI systems with moral patienthood according to the three major theories of well-being. I also discuss what we should do in light of this conflict. If anyone is interested in reading or giving comments on the draft when it is finished, send me a message or an e-mail (adriarodriguezmoret@gmail.com).

• Adrià Moret 18 Mar 2024 18:57 UTC

  13 points

  0 ∶ 0

  on: EA “Wor­ld­views” Need Rethinking

  Thanks for this! I would be curious to know what you think about the tension there seems to be between allocating resources to Global health & development (or even prioritizing it over Animal Welfare) and rejecting speciesism given The Meat eater problem.

• Adrià Moret 4 Dec 2023 10:15 UTC

  4 points

  0 ∶ 0

  in reply to: SebastianSchmidt’s comment on: Tak­ing Into Ac­count Sen­tient Non-Hu­mans in AI Am­bi­tious Value Learn­ing: Sen­tien­tist Co­her­ent Ex­trap­o­lated Volition

  Thank you Seb!

Tak­ing Into Ac­count Sen­tient Non-Hu­mans in AI Am­bi­tious Value Learn­ing: Sen­tien­tist Co­her­ent Ex­trap­o­lated Volition

• Adrià Moret 1 Dec 2023 16:00 UTC

  1 point

  0 ∶ 0

  on: New re­port: “Schem­ing AIs: Will AIs fake al­ign­ment dur­ing train­ing in or­der to get power?”

  Thank you for writing this!