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.
More from AGI Musings
- AI math proofs won't kill understanding: post hoc exploration keeps mathematicians central — njyx · 2026-09-13
- Andreessen: rogue AI cyber attacks smell like false flags, a convenient excuse for regulatory capture — beffjezos · 2026-09-13
- Sam Altman: stopping AI would mean kids dying of curable diseases — firstadopter · 2026-09-13
- 1a3orn's flight-instruments analogy: should AI firms hide model state from users? — 1a3orn · 2026-09-13
- Essay: AI safety is impossible if companies hide LLM state, like planes without instruments — 1a3orn · 2026-09-13
- Anthropic's Dario Amodei calls on AI industry to slow down, draws 'race to IPO' mockery — ryanshrout · 2026-09-13