OpenAI self-replicating prompt was misreported, Zvi clarifies it wasn't found in the wild
TheZvi · x · 2026-09-30
David Krueger called out fast-news AI accounts including @TheZvi and @AndrewCurran for multiple misreports of the OpenAI safety story: the original disclosure only said OpenAI "found a self-replicating prompt," not that replication was observed in the wild. TheZvi apologized, saying his initial reaction was too dismissive and the person was communicating something real, and invited criticism of his full writeup.
Related event: Cambridge researcher debunks misread OpenAI self-replicating prompt claims(4 posts)→
More from Safety
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16