Sean Goedecke wrote an interesting article on using LLMs as a staff engineer. I struggle with LLMs myself and find myself generally agreeing with his take here.
Software engineers are deeply split on the subject of large language models. Many believe they’re the most transformative technology to ever hit the industry. Others believe they’re the latest in a long line of hype-only products: exciting to think about, but ultimately not useful to professionals trying to do serious work.
By way of Sean Goedecke