Codex apps should use the GPT-ultra harness
aaron_lou · x · 2026-07-21
In a reply thread, the author argues that the **GPT-ultra harness** should be the standard harness for commercial **Codex** apps. The follow-up question asks whether the internal version of Codex differs in model choice, harness, or both, highlighting that the real issue may be the surrounding execution stack rather than the model alone.
More from coding & agent
- Codex turns out 123 screensavers in one playful batch — intellectronica · 2026-07-21
- Grok Build adds `grok doctor`, resumable sessions and remote image paste — mark_k · 2026-07-21
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21