Comment by adamddev1 | Hacker News Reader

Comment by adamddev1 | Hacker News Reader

Parent Full thread

I remember when I was just learning how to code and making some web app, I had to do a lot more blind guessing and running. "Ok let me try this... Will that work now?" I remember staying up really late, feeling stuck to the computer in that slot machine mode.

Then when I learned more I got less and less of that guessing feeling. I understood what I was building and what would work, I began using typed languages and could keep on track with the compiler/LSP. This brought me more into a satisfying flow state, and I had less of that addicting "wait let me see if this will work" magic.

It seems like coding with Claude etc is a lot like a trip back to the guesswork stage, and I don't want to go back there.

(Sometimes, when I'm doing some dev-opsy type stuff of stringing a bunch of messy components together or working with a pile of complex APIs, I can feel myself back in the blind guessing territory, and incidentally this is where I find a chat with an LLM most helpful.)

Sadly, I've met too many professional software developers in the industry, who never progressed beyond "Try something, see if it works, then try something else." AI is great for these programmers, since it's somewhat better than what they've done as a career for decades.

It's a trip back to a guesswork stage because most of the training data looks like the process you described your beginnings have been like.

Now you know how to do things first shot. When you write the code, your inner voice reminds you ahead of time to do it like this and that. And that "this and that" is what your prompt needs to have to avoid the trip to guesswork. Working with agents is like working with juniors. If you don't give them the direction and explain how, they'll be as lost as the LLM. The difference is, your brain finds guardrails as you solve the problem, the LLM doesn't have this context, you have to give it upfront. Like, you know, a good manager would.

> The difference is, your brain finds guardrails as you solve the problem, the LLM doesn't have this context, you have to give it upfront. Like, you know, a good manager would

Not really the same feeling. It’s more like speaking a foreign language. At the beginning, you’re always guessing at words, and what’s the correct structure/expression. After a few years, you can go direct from idea to sentences.

Today, my brain is familiar with “computer speak”. More often than not, it goes straight from ideas to algorithms and data structures. My time is mostly spent on checking assumptions (what’s the data type returned by this call,…) and verifying results (debugger, tests, printf,…).

Using LLM is like hiring an unreliable translator when I already know the language. Yes, it may speak faster than me, but I do not a faster pace of conversation.

> Using LLM is like hiring an unreliable translator when I already know the language.

Fantastic analogy. And when you don't really know the language that well you're just amazed at the translator, like "wow you can speak really well!"

Reply on news.ycombinator.com