← Back to context

Comment by mullingitover

6 days ago

> it's almost impossible to get Gemini to not do "helpful" drive-by-refactors

Just asking "Explain what this service does?" turns into

[No response for three minutes...]

+729 -522

22 comments

mullingitover

Reply
cowmoo728  6 days ago

it's also so aggressive about taking out debug log statements and in-progress code. I'll ask it to fill in a new function somewhere else and it will remove all of the half written code from the piece I'm currently working on.

  • chankstein38  6 days ago

    I ended up adding a "NEVER REMOVE LOGGING OR DEBUGGING INFO, OPT TO ADD MORE OF IT" to my user instructions and that has _somewhat_ fixed the problem but introduced a new problem where, no matter what I'm talking to it about, it tries to add logging. Even if it's not a code problem. I've had it explain that I could setup an ESP32 with a sensor so that I could get logging from it then write me firmware for it.

    • bratwurst3000  6 days ago

      "I've had it explain that I could setup an ESP32 with a sensor so that I could get logging from it then write me firmware for it." lol did you try it? This so far from everything ratinonal

      1 reply →

    • sd9  6 days ago

      If it's adding too much logging now, have you tried softening the instruction about adding more?

      "NEVER REMOVE LOGGING OR DEBUGGING INFO. If unsure, bias towards introducing sensible logging."

      Or just

      "NEVER REMOVE LOGGING OR DEBUGGING INFO."

quotemstr  6 days ago

What. You don't have yours ask for edit approval?

  • girvo  6 days ago

    The depressing truth is most I know just run all these tools in /yolo mode or equivalents.

    Because your coworkers definitely are, and we're stack ranked, so it's a race (literally) to the bottom. Just send it...

    (All this actually seems to do is push the burden on to their coworkers as reviewers, for what it's worth)

    • embedding-shape  5 days ago

      You're mixing up two things though. One is what the agent does "locally", wherever that might be (for me it's inside a VM), and second is what code you actually share or as you call "send".

      Just because you don't want to gate every change in #1, doesn't mean you're just throwing shit via #2, I'm still reviewing my code as much as before, if not more now, before I consider it ready to be reviewed by others.

      But I'm seemingly also one of the few developers who seem to take responsibility of the code I produce, even if AI happens to have coded it.

      2 replies →

  • embedding-shape  6 days ago

    Who has time for that? This is how I run codex: `codex --sandbox danger-full-access --dangerously-bypass-approvals-and-sandbox --search exec "$PROMPT"`, having to approve each change would effectively destroy the entire point of using an agent, at least for me.

    Edit: obviously inside something so it doesn't have access to the rest of my system, but enough access to be useful.

  • mullingitover  6 days ago

    Ask mode exists, I think the models work on the assumption that if you're allowing edits then of course you must want edits.

BartShoot  6 days ago

if you had to ask it obviously needs to refactor code for clarity so next person does not need to ask