Agentic coding is undeniably very useful. It’s also very bad. Or rather, it’s having some horrible effects on us, our craft, and our relationships with each other. I can feel it in my bones, and a lot of others can too. But whenever I try to explain what exactly is wrong, I find myself waving my hands wildly and jumping from point to point. Fine, here’s a list. 4 problems with no solution in sight–or, as I call them, the four horsemen of agentic coding.
LLM-generated code has a strong smell that makes codebases repulsive to humans. We quickly came up with a name for it—slop—and it undoubtedly carries a negative connotation. Claude now famously communicates entirely through word salad, and Astra writes in a bizarre competitive code-golfy style, incomprehensible to normal humans. Sloppiness turned out to be a surprisingly persistent property of LLM output and at this point looks like a signature move rather than a growing pain.
Once agents are allowed, they very quickly take over. What used to be a shared space for humans where each team member contributed became an AI wasteland where people don’t want to spend time. Engineers become alienated from code and, as a result, care less. Software engineering used to be a fairly kinesthetic field of work. Agentic coding has dramatically increased the distance between engineers and the product of their work. We don’t experience code directly anymore: we send an agent with a vague set of instructions and then skim through its report.
AI erodes existing skills, impedes learning, and doesn’t offer any meaningful skill progression. There is no shortage of people reporting their wits slipping away after prolonged use of AI.
Source: Hacker News · Summarized by HeadlinesBriefing