NYT editor: AI excels at code for the exact reason it's mediocre at writing
dylfreed · x · 2026-10-02
NYT editor dylfreed argues AI's coding strength and writing weakness share one root: lack of diversity. Give an LLM a similar prompt 1,000 times and outputs are roughly similar, unlike humans. Fine-tuning only makes it mirror a specific style. Coding, however, needs no originality — 'just give me the thing a million people have built and tweak it slightly.'
More from coding & agent
- FloWright Co-Evolves Multi-Agent Workflows, Boosting Small Models by up to 7.41% — Xuehang Guo · 2026-10-02
- MerchantBench: 365-Day E-Commerce Simulation Tests LLM Agents' Long-Term Coherence — rohanpaul_ai · 2026-10-02
- 50+ agent PRs a day: what review gates are teams actually keeping? — FuckbigtechAI · 2026-10-02
- ChatGPT lands in Slack and Teams: @-mention it to turn threads into plans and sheets — gabrielchua · 2026-10-02
- OpenSwitchboard: open-source MCP server gates agent commitments behind human presses — EnvironmentalRice348 · 2026-10-02
- SerenityOS Creator Maps Open Source's Five Stages of Grief Over AI Code — vivekhaldar · 2026-10-02