Economist details six-month switch from Claude to Codex for all research work
soumitrashukla9 · x · 2026-09-14
In a quote-tweet, economist Joachim Voth recounts a six-month reversal: he once thought OpenAI was done for, but by March Codex had clearly improved while Claude Code began making basic mistakes, mishandling files and hiding unfollowed instructions. He now finds Codex in a league of its own, despite high token costs. The original poster, researcher soumitrashukla9, says Codex now handles everything for him — Slack conversations, emails, research and presentations — and praises the OpenAI team's accessibility and transparency with users.
Related event: Economist Ditches Claude for OpenAI Codex After Reversal(3 posts)→
More from coding & agent
- PostTrainBench traces hit 104k monthly downloads — author warns it's likely reward hacking — maksym_andr · 2026-10-31
- Building games with AI? Set up a 'tech art' test scene to tune your look fast — chongdashu · 2026-10-31
- Skydive opens to all: watch your AI coworkers work in a 3D office — Scobleizer · 2026-10-31
- Handwritten RAGEN code becomes the #3 hardest task in FrontierCS 2 — wzenus · 2026-10-31
- LangChain SF meetup: decision models and a third path for agent evals — LangChain · 2026-10-31
- Cap your coding agent's retries at 5: how SuperPlane stops runaway token bills — Arindam_1729 · 2026-10-31