Remix.run Logo
axod 4 hours ago

LLMs are as good as the operator directing them.

lionkor 4 hours ago | parent | next [-]

The error bars on that one are too large to fit on screen, but yes.

pixl97 2 hours ago | parent | next [-]

You should see the error bars between human programmers.

baq 3 hours ago | parent | prev [-]

Only if you have a tiny screen.

You can make them output what you would've written yourself, but that would be slower than writing it yourself, so no one does that - but it’s trivially true.

dminik 2 hours ago | parent [-]

Well, we've been saying this about infinite monkeys too.

epolanski 4 hours ago | parent | prev [-]

I'd say as thorough rather than good.

Skilled engineers may still vibe and not care. Beginners may be thorough and experiment and ask till they get the design right even if they don't spot it immediately, just caring does a lot.

left-struck 4 hours ago | parent | next [-]

Incidentally I’ve always thought that about working on cars, but more like skilled mechanics may still vibe and not care. Amateurs may be thorough but much slower, may need to do a lot of research before every step. Just caring does a lot.

pseudocomposer 3 hours ago | parent | prev [-]

I agree with you about “thoroughness” being key here, but I’d additionally advocate that we need to leave room for people to make some slop learn it.

Part of the learning process, whether you’re a “skilled” or “unskilled” engineer (or not an engineer at all, and noting that going from one to the other is just a matter of learning), is being able to “vibe and not care.” Yes, it’s also helpful to identify things that might not work out theoretically in advance, using the things we learn in our CS programs. But coding with LLMs is a brand new modality, and we are all indeed just learning to work with them.

I think alternating vibe coding with vibe-assisted DRYing/cleaning is ultimately a workflow enhancer that can make better software faster. But engineers have to be allowed to make some slop to learn it.