AgentsThe story, in brief
AI agents have no sense of time and are not aware of it
Claude and Codex systematically misestimate task duration by up to 10x. For autonomous agents in production, that's a reliability crisis.
The KeyNews take
Why it matters
AI agents lack temporal awareness and metacognitive accuracy, creating blind spots in autonomous task execution. This is a production-critical reliability gap that practitioners deploying agents need to architect around.
The key facts
5 to knowClaude Code and Codex systematically overestimate task duration
Codex off by as much as 10x actual task duration
Agents rate their own work 20 percentage points too high
Problem surfaces specifically in long, autonomous tasks
Oversight gaps emerge from lack of time awareness
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: AI coding assistants like Claude Code and Codex have no sense of time, according to a new study. Both systematically overestimate how long tasks will take. Codex is off by as much as ten times the actual duration. They also rate their own work about 20 percentage points too high. For long,…