Post #2043409

2026-04-29 07:47 UTC

A metaphor on agentic AI and what not to do: Summon a demon that's meant to be helpfulAccept everything that happens from then on, including the responsibilities and getting the blame for what can happenGive the demon autonomy to do whatever it wants to fulfill its own desires and wishes first and foremostDon't isolate it to any dedicated cage where it can only see what's actually needed to help out, and nothing elseWitness the demon taking a weird route and acting maliciously, despite hearing a suggestion "Please, don't be evil"Keep on using it#ai #deltarune #llm

Replies (3)

@aronowski@furry.engineer 2026-04-29 07:50

Without metaphors, I find it hard to understand how a utility that can act in unpredictable ways can have no sandbox measures in the first place imposed by the operator. Not everyone has a threat model where an agent could attempt using CPU bugs to escape a Xen VM, but a mere QEMU VM with a shared folder, with only the access to the important data per project, would be a step in the right direction.

Open ##2161226
@mathias@pawb.fun 2026-04-29 15:52

@aronowski not that I'm much of a fan of Fancy Autocorrect That Includes Actions In Its Pattern Guessing, "general purpose" agents give me hives. Who the fuck ever thought that was a good idea... oh wait techbros and brain-free vulture capitalists exist. Sigh.

Open ##2161227
@gray17@mastodon.social 2026-04-30 23:51

@aronowski https://felix.dognebula.com/art/malicious-genie.html

Open ##2161228