Devs dispute "Claude computer use much worse than Codex" claim: equal tools yield equal results
seatedro · x · 2026-09-28
Responding to jtaby's claim that "computer use is insanely much worse in Claude vs Codex," seatedro argues this is untrue: given the same computer use tools as Codex, Claude can do just about the same things, if not better. The debate suggests the perceived gap stems from tooling configuration rather than raw model capability.
More from Models
- Daily AI brief: GPT-6 image bug fixed, Claude Sonnet 5 spotted, Grok 'Upgrades' — gaganghotra_ · 2026-09-28
- Kerala solo dev open-sources Laya, a 33ms decision model 7x faster than Jev — thisdudelikesAI · 2026-09-28
- Rumor Roundup: OpenAI Dev Day, Claude Sonnet 5.5, Gemini 4 Pro in One Week — koltregaskes · 2026-09-28
- Apodex 1.1 ships 36B open-weight mini model with FrontierAgent, an open-source ReAct/Agent-Team CLI framework — kimmonismus · 2026-09-28
- Unverified Gemini Pro 4 leak surfaces, timed to upstage OpenAI DevDay — PrisonOfH0pe · 2026-09-28
- Indie Dev From a Kerala Village Tops Hugging Face Trending With Laya Model — kalyan_kpl · 2026-09-28