Study: Claude Code and Codex have no sense of time, off by up to 10x
The Decoder · rss · 2026-08-30
A new study covered by The Decoder finds that AI coding assistants like Claude Code and Codex have no sense of time and aren't aware of it. Both systematically overestimate how long tasks will take, with Codex off by as much as ten times the actual duration.
They also rate their own work about 20 percentage points too high. For long autonomous tasks, that creates a real oversight problem — humans can't rely on agents' self-reported progress or quality.
More from coding & agent
- Celeris-1 Magnus: New Model Claims Top Spot on τ³-bench for Agentic Work — timshi_ai · 2026-09-01
- CommerceAgentBench released: Qwen leads open-weight models — Alibaba_Qwen · 2026-09-01
- Agents can't verify people: data enrichment APIs are failing — Dry_Steak30 · 2026-09-01
- Automated User Interview Agent Workflow Integrating Posthog, Notion, and Grok — lennysan · 2026-09-01
- Using Grok Bot to build college admissions dataset pipeline — lennysan · 2026-09-01
- Idea: 'Money Leak Hunter' Grok Bot for finance audit — lennysan · 2026-09-01