The 518-Token Sabotage: How OpenAI’s Cost-Cutting Is Making Codex Dumber
Developers noticed GPT-5.5 Codex’s reasoning tokens cluster at 518-token intervals — a telltale sign of batching for cost-cutting. The result: intermittent, predictable failures in complex reasoning. OpenAI optimized for throughput, and users paid the price in quality. The betrayal is hiding in plain sight.