Alex Ewerlöf argues LLM coding is far from production-ready
What happened
作者直接开怼“编程问题已经解决了”这种说法。大模型确实能生成代码，但软件的大头成本在维护、可靠性和安全这些非功能性需求上，而大模型在这些方面基本没谱。它们本质是概率模型，连数清单词里几个字母都费劲，更别说处理大规模逻辑了。在医疗、金融这类容错率极低的行业，AI 没法为错误负责——你总不能给模型判刑或罚款。文章还提到，喊得最凶的那批人，往往自己没东西跑在...
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageAlex Ewerlöf argues LLM coding is far from production-ready
Alex Ewerlöf pushes back on the “coding is solved” narrative. He notes LLMs are good at generating code, but the bulk of software cost lies in maintenance, reliability, and security—the non-functional requirements. LLMs are probabilistic and struggle with logic at scale; they can’t even reliably count letters. In low-tolerance fields like healthcare or finance, AI can’t be held accountable. He adds that the loudest proponents often have nothing running in production.
Heat over time
Not enough continuous observations to draw a trend yet.