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 Launches Always-On Agent Dots Powered by GPT-6 Astra at DevDay(57 posts)→
More from Apps
- OpenAI opens MCP Extensions to build plugins that feel like native ChatGPT features — haltakov · 2026-09-30
- DeepSeek quietly ships Harness GUI desktop app with PTC orchestration and plugin architecture — solyarisoftware · 2026-09-30
- Phonon-2: 164MB open-weights ASR beats Whisper Large at 1/10th the size — julianweisser · 2026-09-30
- ChatGPT Work mode demands root access, locking out users for weeks — Dogbold · 2026-09-30
- Google ships Jetpack Compose A2UI renderer to turn agent streams into native Android UI — rseroter · 2026-09-30
- Subframe relaunches as a canvas for designers who code, copy/paste between both — kevinsxu · 2026-09-30