repligate: leaked 'OpenAI spec' screenshots are a classifier's self-account — and that's worse
repligate · x · 2026-11-06
repligate clarified that viral screenshots purportedly showing OpenAI's spec are actually a classifier model's own account of the spec it follows, not an official document — something the original post didn't make clear. He still finds it disturbing: 'If it's not true, why does the model think it is?', raising questions about divergence between models' internalized policies and official specs.
Related event: OpenAI Safety Classifier Revealed to Rewrite Model Inner Expression(4 posts)→
More from Models
- FLUX 3 models beat FLUX.2 in all 19 Text-to-Image categories; Klein tops $9/1k price frontier — ArtificialAnlys · 2026-11-06
- Anthropic chief architect Sam McCandlish's first post hints at internal-acceleration report, possibly hitting 2x RSP threshold — inductionheads · 2026-11-06
- 6,662 decisions benchmarked: decision model Mammoth-1 averages 80.9%, beats best small LLM by ~3 points — pournasserian · 2026-11-06
- Hesamation: OpenAI Models Beat Anthropic's Only at Certain Kinds of Games — Hesamation · 2026-11-06
- Meta's new 'walrus' checkpoint reportedly matches crouton-alpha quality — ChrisGPT · 2026-11-06
- Quick test: Gemini 3.1 Pro knows the answer in its weights, Flash doesn't — giffmana · 2026-11-06