I've mentioned my own experiences working with AI to navigate the intricacies of Git. Here Jon Udell relays his own experiences. He writes, "What I brought to the table was the knowledge that git bisect was the right tool for the job. Claude Code brought the ability to wield the tool effectively. And as it did so, I watched and learned. This aspect of LLM use is not a black box. When agents run commands on your behalf you can see and approve them. 'I should probably take an online course,' my friend said, 'or watch some videos.' You can, I said, but there's no better learning experience than to be guided through the use of a tool in a situation where you need it to solve a problem in the work you're actually doing." People who create and teach classes for a living should ponder this. The issues of 'cheating' or 'cognitive offloading' are merely distractions obscuring the real impact of what's happening here.
Today: Total: [Direct link] [Share]
