Post

Sam Rose
@samwho.dev

This is where my opinion has landed as well. Most of the “typing” is done by LLMs for my own code these days, but I’m still in my IDE, reading, watching the diffs go by, interrupting to tell it to do something differently, refactoring regularly to make sure the code is legible.

dan@danabra.mov

having used claude extensively for the past couple of months, i think there is still a lot of value to understanding your code and steering it intentionally. the amount of incidental complexity claude accumulates otherwise (which mostly results in bugs that it can't ever fix reliably) is staggering.

Sam Rose
@samwho.dev

And I like this workflow a lot. If I have an idea that’s a big departure from the current state it’s very cheap to try it. I’m iterating with the LLM, I’m using the components I’m building constantly, tweaking small things that feel wrong. I can bring ideas to life I may have skipped on before.

1 repost6 likes

Sam Rose
@samwho.dev

And because I can talk to the LLM with my voice, it can interpret my words very well, it reduces the typing I do and thus the pain I get from tennis elbow. Hopefully those days will be soon behind me, but in the meantime this is a huge win for me.

Sam Rose
@samwho.dev

And this has all made it very clear to me that whenever I see slop in the wild, it has little to do with the LLM. If you aren’t spending the time to make sure what you’ve built meets the quality bar, that’s a you problem. A skill issue, the kids might say. You can build great software with LLMs.

Sam Rose
@samwho.dev

And of course you can build great software without LLMs. If your preferred workflow is to type the code I think there’s nothing wrong with that at all. The “you’re being left behind” narrative is ridiculous. Use the tools if they help you, don’t if they don’t. Everyone needs to grow up, man.

hayleigh
@hayleigh.dev

This is true to a point but we are *rapidly* approaching a state where the volume of LLM output is simply too great to personally review. Then we’re talking about leaning on LLMs for code review in PRs, then soon its about leaning on sub-agents to offload planning…

hayleigh
@hayleigh.dev

Fucking wicked that you’re using them as an accessibility aide though, can we hype this stuff more than all the other ai discourse 😭