Comment by ben_w | Hacker News Reader

Comment by ben_w | Hacker News Reader

Parent Full thread

My experience is also that they're very different from writing code myself.

There are ways to use the tool better and worse, the worst is to blindly fire off the agent and commit the changes without reading them: This *only* works for very small projects, though it often *does* work for those projects.

For bigger projects, you need to use (and enforce use of) the right architecture, and read pull requests rather than saying "LGTM" and clicking accept. Pick the right way to split the project up into discrete components with clear boundaries between them, make sure that the LLM's commits never introduce surprise coupling outside those boundaries, and make sure the unit tests aren't ridiculously brittle, they can be OK.

https://www.youtube.com/watch?v=grPtnrOTP_4

"Make sure to read the commits" seems to be enough for your points 2/3, at least for me. But everyone thinks a bit differently, YMMV. It also means I almost immediately catch most of the (20%? 10%?) of the time the LLM does something wrong, though not all of them.

I find I still have deep focus. If anything, the problem for me is they're so addictive I am tempted to keep working and working rather than rest, a problem I last faced over 20 years ago when I was working on a personal project that ended up not going anywhere.

I do read the commits and really try to understand what the model is trying to do. However, I think this conflicts against what we are really trying to do here: - We want to code faster so we use LLMs - We want to still be in charge, so we spend a lot of time reading and understanding every single commit and review PRs.

Before, we used to build a mental model of the code with every new line of code we wrote. That took time, but the result was a very solid understanding. Now we try to build the mental model by just looking at what the LLM produces. Similar to how students who spend most of their time practicing what they are studying with actual exercises achieve higher grades than those who just read the book, we are now at a disadvantage against our old selves who made the effort of writing the code.

Moreover, an LLM produces code a lot faster than we can read and understand. If we want to achieve an actual speedup in code output, there's no way we can read and understand everything and be faster than before. We have to sacrifice the understanding of some parts. This compounds over time and we quickly get into a place of total reliance on LLMs.

Regarding addiction: I also think these devices are addictive. They do open a lot of new doors for us builders. But I think hour grey matter hardware is not built of this speed. Give it time, the more project ideas you start spinning up, the sooner you'll reach burnout.

> Similar to how students who spend most of their time practicing what they are studying with actual exercises achieve higher grades

This is spot on.

> build a mental model of the code with every new line of code

This idea has been explored in depth in the Peter Naur's excellent paper, "Programming as theory building" [1] (also extensively discussed on HN [2]). If you haven't read it yet, I bet you will enjoy it a lot. :)

[1] https://gwern.net/doc/cs/algorithm/1985-naur.pdf

[2] https://hn.algolia.com/?q=Programming+as+theory+building

Thank you so much for suggesting this, I will definitely enjoy reading it!

Reply on news.ycombinator.com