Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why agents are bad pair programmers

justin.searls.co

Post reply on HN
Print view View original

11–20 of 239 posts

Re: Why agents are bad pair programmers

#11

Post by gen220 »

BowBun wrote: post #4
bluefirebrand wrote: post #2

Pair programming is also not suitable for all cases Maybe not for many cases I mentioned this elsewhere but I find it absolutely impossible to get into a good programming flow anymore while the LLM constantly interrupts me with suggested autocompletes that I have to stop, read, review, and accept/reject It's been miserable trying to incorporate this into my workflow

Second this. My solution is to have a 'non-AI' IDE and then a Cursor/VS Code to switch between. Deep work cannot be achieved by chatting with the coding bots, sorry.

You should try aider! This is my workflow, essentially

Re: Why agents are bad pair programmers

#12

Post by latentsea »

morkalork wrote: post #9
BowBun wrote: post #4

Earlier quoted context omitted.

Second this. My solution is to have a 'non-AI' IDE and then a Cursor/VS Code to switch between. Deep work cannot be achieved by chatting with the coding bots, sorry.

Thirded. It was just completely distracting and I had to turn it off. I use AI but not after every keystroke, jeez.

But but but... "we are an AI-first company".

Yeah, nah. Fourthed!

Re: Why agents are bad pair programmers

#13

Post by johnfn »

flessner wrote: post #8
bluefirebrand wrote: post #2

Pair programming is also not suitable for all cases Maybe not for many cases I mentioned this elsewhere but I find it absolutely impossible to get into a good programming flow anymore while the LLM constantly interrupts me with suggested autocompletes that I have to stop, read, review, and accept/reject It's been miserable trying to incorporate this into my workflow

I recently got a new laptop and had to setup my IDE again. After a couple hours of coding something felt "weird" - turns out I forgot to login to GitHub Copilot and I was working without it the entire time. I felt a lot more proactive and confident as I wasn't waiting on the autocomplete. Also, Cursor was exceptional at interrupting any kind of "flow" - who even wants their next cursor position predicted? I'll probab…

> who even wants their next cursor position predicted

I'm fascinated by how different workflows are. This single feature has saved me a staggering amount of time.

Re: Why agents are bad pair programmers

#14

Post by ramesh31 »

bluefirebrand wrote: post #10
ramesh31 wrote: post #5

>LLM agents make bad pairs because they code faster than humans think This is why I strongly dislike all of the terminal based tools and PR based stuff. If you're left to read through a completed chunk of code it is just overwhelming and your cycle time is too slow. The key to productivity is using an IDE based tool that shows you every line of code as it is being written, so you're reading it and understanding where…

If I have a 20 line function in my mind and the LLM injects 20 lines for me to accept or reject, I have two problems First I have to review the 20 lines the LLM has produced Second, if I reject those lines, it has probably shoved the function I had in mind out of my head It's enormously disruptive to my progress

The hard truth here is in accepting that the 20 lines in your head were probably wrong, or suboptimal, and letting go of that urge. Think in interfaces, not implementations. Successive rendering, not one-shot.

Re: Why agents are bad pair programmers

#15

Post by shortstuffsushi »

ramesh31 wrote: post #14
bluefirebrand wrote: post #10

Earlier quoted context omitted.

If I have a 20 line function in my mind and the LLM injects 20 lines for me to accept or reject, I have two problems First I have to review the 20 lines the LLM has produced Second, if I reject those lines, it has probably shoved the function I had in mind out of my head It's enormously disruptive to my progress

The hard truth here is in accepting that the 20 lines in your head were probably wrong, or suboptimal, and letting go of that urge. Think in interfaces, not implementations. Successive rendering, not one-shot.

This is just fundamentally not the case most of the time. LLMs guess where you're going, but so often what they produce is a "similar looking" non sequitur relative to the lines above it. It guesses, and sometimes that guess is good, but as often, or more, it's not.

The suggestion "think in interfaces" is fine; if you spell out enough context in comments, the LLM may be able to guess more accurately, but in spelling out that much context for it, you've likely already done the mental exercise of the implementation.

Also baffled by "wrong or suboptimal," I don't think I've ever seen an LLM come up with a better solution.

Re: Why agents are bad pair programmers

#16

Post by bluefirebrand »

ramesh31 wrote: post #14
bluefirebrand wrote: post #10

Earlier quoted context omitted.

If I have a 20 line function in my mind and the LLM injects 20 lines for me to accept or reject, I have two problems First I have to review the 20 lines the LLM has produced Second, if I reject those lines, it has probably shoved the function I had in mind out of my head It's enormously disruptive to my progress

The hard truth here is in accepting that the 20 lines in your head were probably wrong, or suboptimal, and letting go of that urge. Think in interfaces, not implementations. Successive rendering, not one-shot.

> The hard truth here is in accepting that the 20 lines in your head were probably wrong, or suboptimal, and letting go of that urge.

Maybe, but the dogshit that Cursor generates is definitely wrong so frankly if it's gonna be my name on the PR then I want it to me my wrong code not hide behind some automated tool

> Think in interfaces, not implementations

In my experience you likely won't know if you've designed the right interface until you successfully implement the solution. Trying to design the perfect interface upfront is almost guaranteed to take longer than just building the thing

Re: Why agents are bad pair programmers

#17

Post by datameta »

ramesh31 wrote: post #14
bluefirebrand wrote: post #10

Earlier quoted context omitted.

If I have a 20 line function in my mind and the LLM injects 20 lines for me to accept or reject, I have two problems First I have to review the 20 lines the LLM has produced Second, if I reject those lines, it has probably shoved the function I had in mind out of my head It's enormously disruptive to my progress

The hard truth here is in accepting that the 20 lines in your head were probably wrong, or suboptimal, and letting go of that urge. Think in interfaces, not implementations. Successive rendering, not one-shot.

I agree with the last two sentences but simultaneously think that starting to defacto believe you cannot have an equal or better solution compared to the AI is the start of atrophy of those skills.

Re: Why agents are bad pair programmers

#18

Post by mdp2021 »

latentsea wrote: post #12
morkalork wrote: post #9

Earlier quoted context omitted.

Thirded. It was just completely distracting and I had to turn it off. I use AI but not after every keystroke, jeez.

But but but... "we are an AI-first company". Yeah, nah. Fourthed!

> AI-first company

Does anybody introduce itself like that?

It's like when your date sends subtle signals, like kicking sleeping tramps in the street and snorting the flour over bread at the restaurant.

(The shocking thing is that the expression would even make sense when taken properly - "we have organized our workflows through AI-intelligent systems" -, while at this time it easily means the opposite.)

Re: Why agents are bad pair programmers

#19

Post by soulofmischief »

BowBun wrote: post #4
bluefirebrand wrote: post #2

Pair programming is also not suitable for all cases Maybe not for many cases I mentioned this elsewhere but I find it absolutely impossible to get into a good programming flow anymore while the LLM constantly interrupts me with suggested autocompletes that I have to stop, read, review, and accept/reject It's been miserable trying to incorporate this into my workflow

Second this. My solution is to have a 'non-AI' IDE and then a Cursor/VS Code to switch between. Deep work cannot be achieved by chatting with the coding bots, sorry.

> Deep work cannot be achieved by chatting with the coding bots, sorry.

...by you. Meanwhile, plenty of us have found a way to enhance our productivity during deep work. No need for the patronization.

Re: Why agents are bad pair programmers

#20

Post by bluefirebrand »

soulofmischief wrote: post #19
BowBun wrote: post #4

Earlier quoted context omitted.

Second this. My solution is to have a 'non-AI' IDE and then a Cursor/VS Code to switch between. Deep work cannot be achieved by chatting with the coding bots, sorry.

> Deep work cannot be achieved by chatting with the coding bots, sorry. ...by you. Meanwhile, plenty of us have found a way to enhance our productivity during deep work. No need for the patronization.

I don't believe you experience deep work the same way I do then

In my mind you cannot do deep work while being interrupted constantly, and LLM agents are constant interruptions

Post reply on HN