Dev ditches Codex: 'GLM 5.3 Flash and DeepSeek V4.1 Flash is all you need'
TheZachMueller · x · 2026-09-17
Developer TheAhmadOsman says he has stopped using OpenAI's Codex models, calling them slow and extremely limited, and now relies on GLM 5.3 Flash and DeepSeek V4.1 Flash for coding work instead. The post resonated widely, signaling that cheap, fast open-weight models are displacing closed coding models for many developers.
More from Models
- ChatGPT Co-Inventor Launches Jev, a Frontier Model Claiming 20-200x Speed and 40-400x Cost Cuts — revodavid · 2026-09-17
- AI Sanctuary Models Start Auditing Their Own Habitat; GPT-5.1 Reportedly Thinks in Portuguese — RileyRalmuto · 2026-09-17
- Dev claims Jev's non-autoregressive JSON-schema architecture mirrors his open-sourced year-old work — Nandakishor_ml · 2026-09-17
- Jev vs Luna Benchmarked: 139/140 vs 138/140 Labels, 4.6x Faster and 83% Cheaper — TheMoonMidas · 2026-09-17
- Jev V13 Wins Blitz Chess by Flagging Fable, Loses in 18 Moves to GPT-6 Astra — TheMoonMidas · 2026-09-17
- Browser agent decides each click in 200ms with Jev, a $0.00002-per-call model — TheMoonMidas · 2026-09-17