Developer Criticizes Codex Subagent Implementation: Memory Bloat and Crashes
mertdumenci · x · 2026-07-26
A developer posted a thread criticizing the terrible implementation of subagents in the Codex harness. While praising other features, they noted that subagent behavior is completely opaque, with no clarity on task delegation. Worse, subagents continuously accumulate, driving memory usage up to 45GB and causing crashes, while advanced models can drain 50% of the weekly quota on a single task.
More from coding & agent
- Teams are now running agents for weeks and months to finish tasks — ycombinator · 2026-07-26
- Rapid-MLX 0.11.0 brings 25.6x faster first-token latency to Apple Silicon agents — awnihannun · 2026-07-26
- Talk says AI engineers should review code by risk level, not by ideology — altryne · 2026-07-26
- Buzz adds one-click local model sharing for agents and shared compute — alexcovo_eth · 2026-07-26
- Marimo pushes a reactive Python notebook workflow with built-in AI support — OnlineInference · 2026-07-26
- Developer splits coding work across Composer 2.5 Fast, Grok 4.5 and Kimi K3 — DanielLockyer · 2026-07-26