Developers say persistent agents run on Anthropic while OpenAI lags on memory
charlespacker · x · 2026-11-12
Developers note that nearly every persistent agent is currently built on Anthropic models. OpenAI's latest models excel at coding but struggle to drive stateful, long-running agents: relatively low proactivity and recurring issues not seen on Claude or even GLM/Kimi.
The core weakness is said to be OpenAI's poor understanding of building good memory (e.g. skills), reflected in low FrontierMemory scores — raising concerns that OpenAI, which was late to coding, will likewise be late on models that truly support persistent agents.
Related event: Developers Say Persistent Agents Run on Anthropic, Not OpenAI(2 posts)→
More from coding & agent
- Coded cartoon show made with Fable 5.2 hints at interactive LLM entertainment — mickeyxfriedman · 2026-11-12
- Dev praises tldraw offline + Omarchy as a rapid prototyping combo — SubtleGradient · 2026-11-12
- Dev rebuilds open-source desk robot Robbi with PCB designed almost entirely by Codex — OpenAIDevs · 2026-11-12
- Mock everything, keep control: a developer's real job in the AI coding era — 0xkarasy · 2026-11-12
- Coded cartoon shows: LLM-written JS episodes could enable interactive entertainment formats — mickeyxfriedman · 2026-11-12
- Set auto-compact window to 400k to cut token usage on 1M-context models — mariofilhoml · 2026-11-12