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

I Am Not a Reverse Centaur

blog.miguelgrinberg.com

Post reply on HN
Print view View original

211–220 of 221 posts

Re: I Am Not a Reverse Centaur

#211

Post by toponijo »

ErroneousBosh wrote: post #155
gedy wrote: post #131

Earlier quoted context omitted.

> I suppose those advocates have more faith in LLM output compared to humans than I do. Some of this is the funny situation where the faithful will state: "This writes better code than I do!" and miss the irony of: "yes, yes it does"

> "This writes better code than I do!" and miss the irony of: "yes, yes it does" I guess it depends on what you consider "better". I've tried using LLMs to write code over the past couple of weeks with extremely mixed results. The LLM certainly writes more interesting code! They like their cute ASCII/unicode animations, don't they? It definitely writes a lot more code, none of it actually correct but some of it funct…

It can write correct code, but it's still really not good at that, at least without lots of prompting. In my experience, that prompting is usually just doing the design/planning work I'd do with or without AI.

Re: I Am Not a Reverse Centaur

#212

Post by aakresearch »

kvark wrote: post #4

We had a process at one company where you had to create an issue before filing a PR. I found it most non-sensical and introducing friction for no good reason. Very surprised to see the author suggesting it in the article. Review is indeed the main bottleneck now for open source, and we need to solve it. Introducing more friction is hardly helping.

In my opinion review will always be a bottleneck, in OS as well as in commercial development.

To my understanding Code Review is first and foremost a trust-building exercise, seeking to establish common understanding behind the piece of code which is to be delivered. That it also may lead to improvements or "catch some bugs" is a distant tertiary side-effect, not the primary goal. At least this is the vantage point I reviewed any code from in the last two decades, and found that team morale and overall quality of teamwork - and delivered software, and customer satisfaction, as a result - responds very well to such interpretation. Regardless of the side you are on and competency level of your vis-a-vis. I would put "elevating competency level of both partners" as a secondary goal of Code Review, and very closely connected to the primary.

With current crop of LLMs there simply nothing on their side to which words "trust" and "understanding" can be meaningfully applied. Hence the "review" takes drastically different shape and implies very different goals. As both the primary and secondary goals described above cannot apply too. The only remaining goal of "improving and bug-catching", in absence of trust, understanding and learning, now requires much more work, which is also much more exhausting.

Re: I Am Not a Reverse Centaur

#213

Post by aakresearch »

aakresearch wrote: post #212
kvark wrote: post #4

We had a process at one company where you had to create an issue before filing a PR. I found it most non-sensical and introducing friction for no good reason. Very surprised to see the author suggesting it in the article. Review is indeed the main bottleneck now for open source, and we need to solve it. Introducing more friction is hardly helping.

In my opinion review will always be a bottleneck, in OS as well as in commercial development. To my understanding Code Review is first and foremost a trust-building exercise, seeking to establish common understanding behind the piece of code which is to be delivered. That it also may lead to improvements or "catch some bugs" is a distant tertiary side-effect, not the primary goal. At least this is the vantage point I…

And a follow-up to my comment above, as wanted to reply to "create an issue before filing a PR" remark too.

I find it actually extremely useful practice. We engineers tend to center our thoughts around "code" and with such code-centric mindset to accumulate knowledge as "code-adjacent" - in repo's commits, PRs, markdown files of all sorts. But in reality most if not all projects extends past the code, and it makes much more sense to have a "project-centered" mindset. As such, an external "issue" captures much more context and provides more useful insight about project impact than PR description alone. Love or hate JIRA, beyond microscopic solo-projects it makes full sense to use broader-scope external tools for project management.

As a nice cosmetic effect it also removes (some) bickering about whether to put "type" or "scope" first in the commit message :). Simply provide a reference to the ticket! (No, really, I hate JIRA, honestly!)

Re: I Am Not a Reverse Centaur

#214

Post by troupo »

projektfu wrote: post #113
troupo wrote: post #50

Earlier quoted context omitted.

"You are not a photographer just because you have a camera" has been a standard saying since forever, and has nothing to do with elitism. Those professionals are professionals not because they own an iPhone and use it to shoot something.

Professionals are professional because someone pays them, that is all.

The word has other meanings, too ;) E.g. "professional conduct" isn't one that is paid for:

1a. of, relating to, or characteristic of a profession

1c.1. characterized by or conforming to the technical or ethical standards of a profession

3. following a line of conduct as though it were a profession

Re: I Am Not a Reverse Centaur

#215

Post by ErroneousBosh »

toponijo wrote: post #211
ErroneousBosh wrote: post #155

Earlier quoted context omitted.

> "This writes better code than I do!" and miss the irony of: "yes, yes it does" I guess it depends on what you consider "better". I've tried using LLMs to write code over the past couple of weeks with extremely mixed results. The LLM certainly writes more interesting code! They like their cute ASCII/unicode animations, don't they? It definitely writes a lot more code, none of it actually correct but some of it funct…

It can write correct code, but it's still really not good at that, at least without lots of prompting. In my experience, that prompting is usually just doing the design/planning work I'd do with or without AI.

I've said this before on here, to much derision as it turns out, but I write my best code in the car. Nowhere near a computer, no distractions, just point the car along the grey stuff and away from the green stuff and think about what I want to write.

Then when I get home, it's just a case of typing it in, which is the bit I'd love to automate away.

My experience with LLMs has been a bit like rubberducking code with someone who's *really* fast at looking stuff up on StackOverflow.

Re: I Am Not a Reverse Centaur

#216

Post by projektfu »

troupo wrote: post #214
projektfu wrote: post #113

Earlier quoted context omitted.

Professionals are professional because someone pays them, that is all.

The word has other meanings, too ;) E.g. "professional conduct" isn't one that is paid for: 1a. of, relating to, or characteristic of a profession 1c.1. characterized by or conforming to the technical or ethical standards of a profession 3. following a line of conduct as though it were a profession

Professionals can be unprofessional, and amateurs can show professionalism, but only one gets paid.

Re: I Am Not a Reverse Centaur

#218

Post by skydhash »

jrm4 wrote: post #207
skydhash wrote: post #93

Earlier quoted context omitted.

As soon as you’re specifying instructions for the computer to do a task automatically, you’re programming it. It can be recording a macro, writing a script, describing it in something like Shortcuts,… The core thing is automation.

Not convinced this is clear at all? I'm typing a document in, lets say -- word. I want it to say "Come to my awesome awesome awesome party." If I type it out, it's not programming, but if I ctrl-c + then ctrl-v twice, it is?

Copy-pasting is not programming, no more than clicking the save button is. But text expansion may be seen as such, especially when it involves dynamic elements (like current date and time). It may not be a clean delineation but, IMO, it's the difference between writing a recipe and doing the dish. Copy-pasting twice is making a dish. Creating a button that let the computer do it is writing a recipe.

Re: I Am Not a Reverse Centaur

#219

Post by joshka »

I agree with the core maintainer complaint here: PR slop is bad, and maintainers should not be forced into reviewing code the submitter does not understand.

But I think the answer is not “don’t slop me, all you sloppers.” The better answer is closer to: “what problem were you trying to solve?”

There is no obligation to treat every PR as merge-ready code. A PR can also be a concrete issue report or a proof-of-concept for a bug. It can say: I found a problem, I investigated it, and code was the clearest way to show where I think the issue lives and how it might be addressed. Use or ignore the implementation as you like. Human-language descriptions are not always the best way to communicate something you've already traced through the codebase.

That can be a high-value contribution even if the code itself is not accepted. It moves the conversation from “I want X” to “here is where X touches the codebase, here is a failing case, here is a possible direction, here are the tradeoffs I noticed.”

The social contract should be that the contributor does not dump review debt on the maintainer. Mark it as a prototype. Explain the problem in your own words. Say what you tested. Say what you are unsure about. Be willing to revise or accept that the maintainer may throw the patch away.

But once framed that way, the relevant question is not whether AI was used. It is whether the PR reduces ambiguity or increases burden.

A sloppy PR that demands review is bad. A prototype PR that explains a real problem is often useful.

Re: I Am Not a Reverse Centaur

#220

Post by notpushkin »

WhitneyLand wrote: post #187

The PR quality problem is legit and needs a solution. But saying his opinion hasn’t changed on this: “the main and most important reason why GenAI tools do not work for me is that they do not make me any faster.” It’s been a year and agents and models have improved dramatically. I can see for some things it doesn’t make sense, but not using it at all because there’s nothing it can help with? Devs who don’t use models…

> It’s been a year and agents and models have improved dramatically.

Then why is the PR quality still a problem?

Post reply on HN