However, there is good reason to fight those tendencies. Tokens don’t appear to be getting cheaper anytime soon. Continually encountering friction, learning, and gaining experience will at the very least give you the advantage in a future if tokens are no longer subsidized to you. And if you do have unlimited reign of tokens, that gained experience gives you the power to come up with better solutions, introduce friction, and fight slop-level outcomes. So it may be worth it to take a step back from an LLM output at different points in time, talk to other humans, invest in a course from a content educator, or maybe think about that hard problem as your falling asleep and dream about it through the night.

I agree with the author - learning how to learn is a useful skill. I must admit that I am not a conscious learner i.e. I still don’t know the exact process on how I learn. However, I do know that I learn by tinkering and doing.

As a result LLMs have been a great boon for me to do and learn.

Creation is often about repetition and having fun and that first thing that you attempt to create is often a copy / something that’s inspired you and then you embracing the various constraints to create it.

The author seems to be of the opinion that coding agents are not a constraint and hence the learning is limited. I can certainly see that angle of thinking. I think there is a counter angle: LLMs =unblock something that prevented creation in the first place and there is learning that happens.

To me, learning is a mindset - it’s the openness and curiosity that attempts to dig into the process of creation and repeat and have fun doing it. So, respectfully, if you want to use tools to help you through that process, imho, don’t let other people’s opinions, block you!

Source: georgerodier.com