Sebastian Raschka asks OpenAI: how are Dots different from a Codex prompt?
rasbt · x · 2026-09-30
After OpenAI unveiled its always-on agents called Dots, ML author Sebastian Raschka publicly asked OpenAI how the demoed use cases — like migrating a website off a legacy codebase — differ from simply writing a Codex prompt, and whether Dots is just an outer loop on top of the Codex chat loop. The question captures the community's core concern about the product: does the always-on form bring genuinely new capability, or is it just packaging?
Related event: OpenAI DevDay 2026: GPT-6.1 Sol, Dots, Ultrafast and 20+ Launches(232 posts)→
More from Apps
- Two prompt rules to kill the AI voice: keep it under 3 sentences, no rhetorical endings — yihui_indie · 2026-11-15
- Japan Gov spotlights miwo, the AI app that reads 1,000-year-old kuzushiji script — tkasasagi · 2026-11-15
- Gemini in Chrome adds Mac menu bar presence and global shortcut, mocked as a sign of Google's desperation — daluoseo · 2026-11-15
- DeepSeek open-sources chat-demo, a backend-free browser chat UI for its API — huangyun_122 · 2026-11-15
- Thai Researcher Builds AI App Making 1,000-Year-Old Japanese Classics Readable to All — tkasasagi · 2026-11-15
- Custom GPTs retire Dec 11: chats won't migrate to Projects, key FAQ points — Ok_Negotiation_2587 · 2026-11-15