Comment by jes5199
6 days ago
I’ve been using Claude (via Cursor) on a greenfield project for the last couple months and my observation is:
1. I am much more productive/effective
2. It’s way more cognitively demanding than writing code the old-fashioned way
3. Even over this short timespan, the tools have improved significantly, amplifying both of the points above
This mirrors my experience and those I've talked to.
LLM assisted coding is a way to get stuff done much faster, at a greatly increased mental cost / energy spent. Oddly enough.
The small dopamine hits you get from "it compiles" are completely automated away, and you're forced to survive on the goal alone. The issues are necessarily complex and require thinking about how the LLM has gotten it subtly wrong.
Painful, but effective?
> Oddly enough.
i actually dont find that outcome odd at all. The high cognative demand comes from the elimination of spurious busy work that would normally come with coding (things like syntax sugars, framework outline, and such). If an AI takes care of all of these things, and lets an author "code" at the speed of thought, you'd be running your engine at maximum.
Not to mention the need to also critically look at the generated code to ensure it's actual correctness (hopefully this can also be helped/offloaded by an ai in the future).
> It’s way more cognitively demanding than writing code the old-fashioned way
How are you using it?
I've been mainly doing "pair programming" with my own agent (using Devstral as of late) and find the reviewing much easier than it would been to literally type all of the code it produces, at least time wise.
I've also tried vibe coding for a bit, and for that I'd agree with you, as you don't have any context if you end up wanting to review something. Basically, if the project was vibe coded from the beginning, it's much harder to get into the codebase.
But when pair programming with the LLM, I already have a built up context, and understand how I want things to be and so on, so reviewing pair programmed code goes a lot faster than reviewing vibe coded code.
I’ve tried a bunch of things but now I’m mostly using Cursor in agent mode with Claude Sonnet 4, doing small-ish pull-request-sized prompts. I don’t have to review code as carefully as I did with Claude 3.7
but I’m finding the bottleneck now is architecture design. I end up having these long discussions with chatGPT-o3 about design patterns, sometimes days of thinking, and then relatively quick implementation sessions with Cursor
It will be interesting to see if and how all of this improves standards around how we document the architecture and concepts of software.
> 2. It’s way more cognitively demanding than writing code the old-fashioned way
Funnily, enough, I find the exact opposite. I feel so much relief that I don't have to waste time figuring out every, single detail. It frees me up to focus on architectural and higher level changes.
I guess what I mean is, I found the details sort of “mindless” before. Code that I could write in my sleep. Now I only have to do the thinky parts
This means that you fully trust the LLM to get the details right.