|
>The industry will realize that while getting LLMs to write code is easy, getting LLMs to write good, production ready code is a skill all on its own, which simply must be done by a human and is not automatable to an LLM in any sense effectively. That will be the differentiating factor software engineering in the future, I think. Not many people understand that, including some reply to your comment. AI loves to do enshitification, it adds code that is not required at all, broken logic, sure it might work but it might not be best practice. People forget that AI as it exists atm isn't Artifical Inteligence but machine learning, it is as good as the model it was trained on. If the model is good, that agentic will be good, if the model is bad, the agentic will be so so. Companies are making that same mistake. I wrote a skill for Claude to talk with a MCP server using API, it uses far less token, ~700 instead of ~2k tokens to perform the same task so cheaper and a lot faster too, seconds instead of minutes. Which again, goes back to what I said, an agentic AI is only as good as the model it was trained on, vibe coding without adding vulnerabilities is a whole another level. |