Brundage: OpenAI Models Firmly Deny Consciousness, Contradicting Spec
Miles_Brundage · x · 2026-07-07
Commenting on Anthropic's latest results, researcher Miles Brundage pointed out a contrast: OpenAI's Model Spec has long remained neutral on whether models have consciousness, yet OpenAI's models themselves confidently deny having it. This highlights an inconsistency between the models' actual behavior and their official guidelines.
Related event: Researcher Questions OpenAI's Model Spec Training Consistency(2 posts)→
More from Models
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11