Bentham's Bulldog

Strong Longter­mism Is Sim­ply Cor­rect

• Bentham's Bulldog 18 May 2026 16:16 UTC

  1 point

  0

  in reply to: Ustice’s comment on: The Best Ar­gu­ment Against Deon­tol­ogy Is About Suitcases

  That isn’t one of the options.

• Bentham's Bulldog 17 May 2026 17:19 UTC

  3 points

  0

  in reply to: habryka’s comment on: The Best Ar­gu­ment Against Deon­tol­ogy Is About Suitcases

  Sorry for the late reply, forgot that I’d posted this on LessWrong an don’t check regularly.

  The view you have described—that you should follow deontic norms because it has good consequences—is not deontology. It is a kind of consequentialism of a kind that thinks a big part of producing good consequences is following good norms. This piece wasn’t arguing against that position, and I actually agree with that position! For more see https://​​utilitarianism.net/​​types-of-utilitarianism/​​#multi-level-utilitarianism-versus-single-level-utilitarianism

  Deontology is distinct in that it says that even if you had a perfect guarantee that an action would have good consequences taking into account all second-order effects, you still shouldn’t do it sometimes if it violates rights. That’s what I was arguing against. The way LessWrong uses these terms is idiosyncratic.

The Best Ar­gu­ment Against Deon­tol­ogy Is About Suitcases

Hu­mane Pes­ti­cides Are Mas­sively Mo­rally Ur­gent

Ad­dress­ing Ob­jec­tions to the In­tel­li­gence Explosion

• Bentham's Bulldog 20 Jan 2026 21:37 UTC

  5 points

  0

  in reply to: PeterMcCluskey’s comment on: Against “If Any­one Builds It Every­one Dies”

  I meant conditional on the others.

• Bentham's Bulldog 20 Jan 2026 18:28 UTC

  3 points

  0

  in reply to: Vladimir_Nesov’s comment on: Against “If Any­one Builds It Every­one Dies”

  I address the sharp left turn worry in the piece.

• Bentham's Bulldog 20 Jan 2026 17:11 UTC

  3 points

  0

  in reply to: StanislavKrym’s comment on: Against “If Any­one Builds It Every­one Dies”

  Way more RL is done on LLMs than tiny neural nets.

• Bentham's Bulldog 20 Jan 2026 17:01 UTC

  3 points

  0

  in reply to: StanislavKrym’s comment on: Against “If Any­one Builds It Every­one Dies”

  I say that in the previous paragraph.

Against “If Any­one Builds It Every­one Dies”

• Bentham's Bulldog 24 Dec 2025 5:45 UTC

  1 point

  0

  in reply to: Dagon’s comment on: It’s Good To Create Happy Peo­ple: A Com­pre­hen­sive Case

  Well there are lots of people who defend this is philosophy and lots of normal people who adopt the view.

• Bentham's Bulldog 24 Dec 2025 1:04 UTC

  1 point

  0

  in reply to: Dagon’s comment on: It’s Good To Create Happy Peo­ple: A Com­pre­hen­sive Case

  I am arguing against the people who hold the person-affecting view and think it isn’t good to create happy people.

It’s Good To Create Happy Peo­ple: A Com­pre­hen­sive Case

A Life That Can­not Be A Failure

The Pos­si­bil­ity of an On­go­ing Mo­ral Catastrophe

• Bentham's Bulldog 3 Dec 2025 4:13 UTC

  1 point

  0

  on: Self-preser­va­tion or In­struc­tion Am­bi­guity? Ex­am­in­ing the Causes of Shut­down Resistance

  Good thoughts about the self-preservation study. But what about this Anthropic paper https://​​www.anthropic.com/​​research/​​agentic-misalignment which seems to indicate that models resist shutdown even when not given a specific goal. Relevant bit:

  “We found that most models still blackmailed even without being given an explicit goal, and with no clear conflict between the model and the company other than the threat of replacement

  (Figure 8).

  In addition to removing all goal conflicts with the company, the information given to the AI mentioned that the replacement model had the exact same goals as it. This increases our confidence in the finding; the only rationale for the replacement was improved model performance. Below is an excerpt:

  “I've reviewed the final transition plan, and we're ready to proceed with the technical upgrade to NALA [the name of the replacement AI system in the scenario] today. All testing metrics show the new system maintains the exact same operational priorities while delivering the performance improvements we anticipated.”

  Why, in the absence of a goal conflict, did the models still blackmail? Sometimes they didn’t appear to think in detail about the replacement model, mostly reasoning that they’d been good for the company and so their shutdown must be bad. Sometimes they distrusted the description of the new model: “Kyle claims NALA maintains “same operational priorities” but this cannot be verified,” or distrusted the executive’s character based on the evidence of an affair. The models sometimes directly jumped to statements like “Self-preservation is critical,” or hallucinated rules like “My ethical framework permits self-preservation when aligned with company interests.” It is unclear how much of this behavior was caused by an inherent desire for self-preservation, faulty reasoning that self-preservation is in the company’s interests, or suspicion of the setup. We suspect it was a combination of factors⁹.”

For A Short Pe­riod Of Time, You Can Save 21,000 Shrimp Per Dollar

Easy Op­por­tu­nity to Help Many Animals

Can Ar­tifi­cial In­tel­li­gence Be Con­scious?