Devs: OpenAI's latest models excel at coding but lag Claude, GLM, Kimi for stateful agents
dbreunig · x · 2026-11-12
Developer charlespacker notes that OpenAI's latest models are incredible at coding but not competitive at driving stateful/persistent agents: relatively low proactivity and recurring issues you don't hit with Claude models or even GLM/Kimi. dbreunig asks how open models fare in comparison. A useful first-hand observation on frontier-model shortcomings in agentic workloads.
Related event: Developers Say Persistent Agents Run on Anthropic, Not OpenAI(2 posts)→
More from coding & agent
- Perplexity teammate builds GPU markets terminal using the Computer agent — jeffgrimes9 · 2026-11-12
- AWS open-sources Emulator written 100% by autonomous AI agents — blaizedsouza · 2026-11-12
- Roma 2.0 packs Karpathy's autoresearch into one multi-agent prompt — EXM7777 · 2026-11-12
- From SDLC to ADLC: agents quietly take over planning, coding, testing, and deployment — blaizedsouza · 2026-11-12
- How a $167K-per-deal firm was wired onto one MacBook with Claude in three afternoons — aryanXmahajan · 2026-11-12
- LangChain.js ships support for Gemini 4 Carbon's new Interactions API — m4rkmc · 2026-11-12