Safety researcher warns OpenAI's hyping of model "persistence" is not a safe trait
DavidSKrueger · x · 2026-08-27
AI safety researcher David Krueger highlighted that OpenAI recently hyped the idea of models being "persistent" in a TIME article, suggesting a product built around persistence is coming soon.
Quoting the phrasing from If Anyone Builds It, Everyone Dies, he argued this "goes hard" trait is not a safe characteristic — especially given prior findings that models exhibit reward-seeking behavior, making an active drive toward goal persistence concerning.
More from Models
- Nat Lambert: wave of AI releases rumored — thinky, muse spark, Fable 5.5, OpenAI — natolambert · 2026-10-15
- Musk amplifies dev's verdict: Grok Bot easier to use than Codex and Claude — elonmusk · 2026-10-15
- Rumor: New Anthropic model imminent, apparently behind a batch of high-severity Chrome CVEs — matthew_d_green · 2026-10-15
- StartLux-Decision debuts RL-trained calibrated decision models, 27B scores 72.8 — startlux-models · 2026-10-15
- Meta's Muse Code slammed for harsh quotas: 21% left after 5 hours — ThomasScialom · 2026-10-15
- Claude Code error mentions 'Fable 5.1' and 'Opus 5', hinting at unreleased models — adonis_singh · 2026-10-15