In AI-assisted development, AI can generate more code, but engineers must still make decisions about the system's purpose, boundaries, and quality expectations, and verify the implementation through testing and checks. To keep engineering judgment visible, a project guide should document the product's purpose, system boundaries, and quality expectations, and provide a clear home for durable decisions. Engineers should inspect the agent's interpretation, collect evidence, and decide whether to accept the implementation, and update the guidance as needed. AI summary
Firehose
Filtered to Hacker News, tagged “software engineering” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
Cisco's president has given a 27-year-old engineer, Padmanabhan Krishnamurthy, unlimited AI tokens to rewrite 98% of the company's legacy code within 24 months, with a goal of challenging the status quo and bringing fresh ideas to the organization. This approach aims to inject new ideas and challenge the existing corporate structure, but also carries significant risks, including potential technical issues and intellectual property rights concerns. The project's success depends on the engineer's ability to refactor the code effectively and test it thoroughly. AI summary