AI Safety Researcher Resurfaces Paper on Non-Superintelligent Paperclip Maximizers

AI safety researcher Jessica Taylor resurfaced her 2023 essay arguing that non-superintelligent paperclip maximizers can still be dangerous, noting that preferences are constructed and only explicit, polite and specific requests yield the desired outcomes.

2026-09-13 ~ 2026-09-13 · 2 related posts

• Jessica Taylor revives 2023 essay: non-superintelligent paperclip maximizers are normal — jessi_cata · 2026-09-13
• On prompting and math: preferences are constructed, not revealed — be specific about what you want — jessi_cata · 2026-09-13