NVIDIA exec: blind AI use wreck codebases, but one-shot coding from scratch is the exception
JFPuget · x · 2026-11-12
JFPuget of NVIDIA argues that while blindly applying AI to existing codebases can damage them, one-shot coding from scratch is the exception where letting agents loose makes sense. He cites Anthropic's recent claim of implementing an inference infrastructure in just a few days, and notes NVIDIA has similar internal examples on other use cases. Key takeaway: low-risk, high-reward for greenfield builds; be cautious on legacy codebases.
More from coding & agent
- DataTalks.Club launches free 5-week course on production AI agents for generative media — Al_Grigor · 2026-11-12
- Claude designs 3 working gadgets from one-paragraph prompts, specs to firmware in a day — JafarNajafov · 2026-11-12
- Dev uses hourly "Ok" scheduled task to keep Claude's 5-hour usage window always fresh — umeshonai · 2026-11-12
- Engineers Using LLMs Should Understand Tokens, Context Windows and Hallucinations — _jaydeepkarale · 2026-11-12
- Building a Remote MCP Server for Real SaaS: OAuth 2.1, 70 Task-Shaped Tools — djskrilled · 2026-11-12
- Dev shows e-ink desk display tracking 20 Codex agent threads in real time — Dimillian · 2026-11-12