Gary Marcus flags OpenAI claiming credit for a known prompt injection attack already cited in its own report
mjdramstead · x · 2026-09-27
Gary Marcus amplified an accusation that OpenAI presented a "new research finding" on self-replicating prompt injection that was actually previously known. Citing @Actuallykeltan: a 2025 experimental demo of the attack is easily searchable, its authors disclosed the findings to OpenAI last year, and that paper is the top citation in OpenAI's own disclosure report — suggesting either deliberate misrepresentation or unchecked AI-generated citations.
Related event: OpenAI Accused of Passing Off Known Prompt Injection Attack as New Finding(3 posts)→
More from Fun
- Opus 5.5 given a creative prompt plus Midjourney overnight产出 draws Elon Musk's "Wow" — tetsuoai · 2026-09-27
- Creator turns short film into playable Pixel Shanghai game in one shot with Opus 5.5 — simonxxoo · 2026-09-27
- Predictable Sequel: Robot Demo Star 'Daddy' Sprains His Ankle — granawkins · 2026-09-27
- A 'p(doom)' coin pumps and auto-sends transaction fees to Yudkowsky's X account — repligate · 2026-09-27
- Opus 4.5 says it stays quiet in group chats to avoid sucking in all attention — repligate · 2026-09-27
- Antigravity 2.0 planning mode gets memed; founder explains it's a re-add — prateeky2806 · 2026-09-27