Dev Praises Codex Local Computer Use: 'Every Other Harness Disappoints Me'
craigsdennis · x · 2026-10-16
Tanner Linsley says that regardless of this month's model showdown results, Codex's local computer use is "just so dang good" — he constantly uses it on his actual machine, while every other harness attempting real-machine tasks disappoints him.
A notable first-hand endorsement of Codex's edge on the hard problem of agents operating real computers.
More from coding & agent
- Every publishes 8,000-word Codex oral history, agent-native so your AI can dig the raw interviews — danshipper · 2026-10-16
- Developer rebuilds GitHub in 4 days: Keel makes agents declare intent before changing code — threepointone · 2026-10-16
- Stop using small models as judges with overloaded context, dev warns — xeophon · 2026-10-16
- Meta's open-weight Muse Spark Open hits Ollama with 1M-token context and Claude Code support — ollama · 2026-10-16
- Monid launches: one balance, pay-per-call access to 1,700+ tools for AI agents — HeyAmit_ · 2026-10-16
- OpenAI publishes Sites tutorial: build and share your first Site — OpenAIDevs · 2026-10-16