Dev after 2 days: Claude is excellent, Codex great for long-horizon tasks but poorly designed
cneuralnetwork · x · 2026-09-29
Developer @cneuralnetwork shares impressions after two days of use: Claude is simply excellent, while Codex handles long-horizon tasks well but suffers from poor design.
More from coding & agent
- Sandboxes will shift from cloud devboxes to one ephemeral environment per command, with snapshots in between — ivan_bezdomny · 2026-09-29
- Claude's fraud detector scored F1 0.87 — until data leakage was fixed and it fell to 0.70 — hugobowne · 2026-09-29
- Machine Payments Protocol Explained: AI Agents Can Now Pay, Not Just Think — jeff_weinstein · 2026-09-29
- ChatGPT Located SSD Sectors and Rebuilt a Deleted Blender Project from Scratch — Winter-Mix-5155 · 2026-09-29
- Opus 5.5 Orchestrating Sonnet Subagents Fixed 600 Issues Overnight — edwinarbus · 2026-09-29
- METR Researcher Builds Human-Review Monitor to Block Suspicious Agent Tool Calls — idavidrein · 2026-09-29