David Cramer, co-founder of Sentry, has expressed skepticism about the productivity benefits of large language models (LLMs). In a post on X, Cramer argued that while LLMs lower entry barriers, they produce complex, hard-to-maintain code that slows long-term development. He criticized the "agentic engineering" approach, where models autonomously generate and deploy code, citing poor code quality and performance issues in complex codebases.
Cramer specifically mentioned tools like OpenClaw, suggesting they generate excessive code that becomes unmanageable. He emphasized that software development remains challenging and is not about code quantity. His views are based on his experience with mature codebases, noting that his recent increased contributions stem from interest rather than ease, indicating a psychological rather than practical shift.
Sentry Co-founder Criticizes LLMs for Hindering Long-term Development
Disclaimer: The content provided on Phemex News is for informational purposes only. We do not guarantee the quality, accuracy, or completeness of the information sourced from third-party articles. The content on this page does not constitute financial or investment advice. We strongly encourage you to conduct you own research and consult with a qualified financial advisor before making any investment decisions.
