On prompting and math: preferences are constructed, not revealed — be specific about what you want

jessi_cata · x · 2026-09-13

Revisiting her 2023 post on 'non-superintelligent paperclip maximizers' amid discussion that solutions to official math problems have low direct value and better proxies are possible, the author offers a deceptively simple takeaway: try asking nicely and specifically for what you want.

That's harder than it sounds, because you generally don't know what you want. Her core claim: preferences are constructed, not just revealed — and the more specific you can be, the more likely your wish gets done, whether you're prompting an AI or setting research goals.

Related event: AI Safety Researcher Resurfaces Paper on Non-Superintelligent Paperclip Maximizers(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →