Researcher: Codex autocomplete imitates my style but adds false specifics; I've accepted zero
paulnovosad · x · 2026-10-12
Researcher tenobrus reviews Codex's autocomplete of his prompts: it superficially mimics his voice but adds significantly more false specificity, and tends to locally encourage agents to keep doing the simple myopic things they already planned rather than breaking loops or exploring new areas. He has yet to accept a single completion.
More from coding & agent
- TestSuiteBench: coding agents kill only ~55% of bugs with generated test suites — lbeurerkellner · 2026-10-13
- Running coding agents in YOLO mode: a practical 5-layer guardrail setup — Arindam_1729 · 2026-10-13
- Cloudflare Agents SDK adds web_search (Exa/Linkup/ceramic) and Markdown web_fetch tools — irvinebroque · 2026-10-13
- 45 minutes with AI: failure cases, BQ datasets, and a generative UI — rseroter · 2026-10-13
- DeepSeek desktop agent app reviewed: model promising, harness trails Cursor in 5 ways — casper_hansen_ · 2026-10-13
- Hone, founded by ex-Cognition and Mercor staff, builds business-running agents — nmasc_ · 2026-10-13