Anthropic user tries Codex, pairs Sonnet 5 with Opus 4.8 as advisor
A user on Anthropic's Max x20 plan picked up OpenAI's Codex on the Pro plan to try it out, switching their coding tool to opencode in the process. They avoided Fable because their work sessions often run longer than 20 minutes. Their usual setup pairs Sonnet 5.0 as the main model with Opus 4.8 acting as an advisor, plus task-specific .
They found it amusing watching Claude argue with the advisor model at times. On a — repurposing an old Razer Blade laptop with a 3080 GPU to offload OCR (optical character recognition) work for a document scanner — Claude wasn't resolving an issue quickly, so they switched to Sonnet 5.6. That model correctly diagnosed that the login manager was consuming VRAM and causing an (OOM) crash, then separately identified overheating during longer runs, and fixed fan-control code that had been reporting incorrect lower limits.
It took some back-and-forth guidance, but the problem got solved. They also noted tighter security behavior, receiving multiple warnings about Claude had implemented or about leaked — nothing major, but useful findings.
Key points
- Switched from Anthropic's Max x20 plan to also try OpenAI's Codex on the Pro plan, moving their tooling to opencode
- Regular setup: Sonnet 5.0 as main model, Opus 4.8 as advisor, plus task-specific
- Sonnet 5.6 correctly diagnosed a two-stage hardware issue — VRAM exhaustion causing OOM, then overheating — on a laptop-based OCR
- Also fixed buggy fan-control code that was misreporting its lower limits
- Multiple security warnings appeared about implemented and leaked — minor but useful