Most AI coding slop comes from being too complacent with agents, says JPMorgan quant researcher
JFPuget · x · 2026-10-08
Jean-François Puget, chief quantitative research officer at JPMorgan, argues that most AI coding slop stems from people being too complacent with their agents — trusting outputs without challenging them. His own approach: give coding agents an extremely hard time (politely, but unreasonably demanding by human standards). The takeaway: treat agents as subordinates to be rigorously reviewed, not oracles to be accepted.
More from coding & agent
- Agents love tidying up files nobody asked them to touch — JFPuget · 2026-10-08
- Open-source bridge turns a browser chat tab into an OpenAI-compatible API endpoint — harshanacz · 2026-10-08
- GraphRAG Bug: Deleted Documents Stay Indexed and Retrievable After Updates — JeremyCMorgan · 2026-10-08
- Paper: Vibe Coding Kills Open Source as AI-Recommended Repos Lose Stars — soumitrashukla9 · 2026-10-08
- Every publishes definitive guide to Compound Engineering, the philosophy behind 7k-star plugin — every · 2026-10-08
- Claude Haiku 5.5 matches GPT-6 Luna pricing but a stingier tokenizer hides a 1.25x cost hike — Simon Willison · 2026-10-08