|
|
|
|
|
|
by throw1234567891
13 days ago
|
|
|
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. |
|
|
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.