As someone who operates an internal AI code review platform for a large engineering org. Trust me, you want this.
There are countless defects that regularly slip by human review. It’s one of the few places that AI adds immediate, low-risk value.
That aside, though, this is unfortunate. And the author and maintainer of these packages is entirely within their rights to do this as a form of protest.
I hate AI and wish it would disappear but you’re right. The automatic PR reviewing LLM at my job genuinely catches a lot of issues that would fly under the radar normally. Obviously a human review is still needed but those downvoting clearly do not work in tech because it’s basically just a fancy SonarQube* CircleCI (well, apparently they’re AI now but before they did that). If it’s wrong, resolve the issue with one click; if it’s right, then its beneficial?
The blanket AI hate is stupid because it drowns out the valid criticisms like energy use, knowledge loss, unmaintainability, etc
edit: I said CircleCI but was thinking of SonarQube
I don’t entirely get the point you’re making but if I’m understanding it correctly my response would be that I’m not pro AI. The issue is that the AI vs not AI conversation always lacks any nuances which means those on the fence just disregard anything being said as just two evangelical bases yelling at each other
We can appreciate the positive aspects of things in tech even if the technology as a whole is a massive problem.
Edit: my point being: can you tell me why PR reviews generated by an LLM are bad? If the discussion was actually diving into the details then I’d be interested but blanket statements are just stupid
We can appreciate the positive aspects of things in tech even if the technology as a whole is a massive problem.
See, I don’t agree with this, and that’s why I see it as “stupid” to have a discussion about the nuance of LLM use.
“Damn, the mushroom cloud coming off of that bomb is hella dope tho”, “woah, look at the speed that projectile gets fired at! I didnt even see it hit me”, “actually, those drones can carry water to put out forest fires as well as explosive devices”. etc.
if i have to trust you then doesn’t that kinda show why the technology isn’t particularly useful? Surely it should be able to speak for itself, rather than need you to vehemently insist that “actually it’s really good you guys just don’t get it”.
Sure, maybe it’s fantastic at reviewing PRs. I could imagine that. But
Trust me, you want this.
is pretty condescending, implying those against it haven’t thought it through. I personally could list about twenty reasons for not using AI, many of them infinitely more important than code being well reviewed.
Having used these at my day job I can understand the policy against them. Ours is fairly well tuned by the people who operate it, adapted to our codebase, and its comments are usually on point, but its false positive rate for my own PRs is still in the low double digit percent range (feedback that’s factually wrong, not relevant to the PR, not scoped appropriately, etc). Before all that tuning, back when we first started using it, I probably went days or weeks without seeing a well-founded suggestion from the tool. Incorrect comments still create work for the PR author (investigating, double checking, etc), they create noise for human reviewers, and ambiguity about whether a change is ready to be merged. I read that policy as being against random people pointing their own review tools at PRs for this project, which I assume would be more on the high false positive/high noise end of the spectrum (i.e., not being tuned for this specific project). I can totally see why already busy maintainers would want to spare themselves from a bunch of poorly calibrated noise.
One nice thing about them compared to human reviewers is that you can just tell them to (professionally) fuck off if they’re wrong without hurting their feelings or having an HR conversation.
Do you work in tech? How often do you submit PRs? AI reviews are one of the best applications for the technology and non-LLM CI tools have existed for ages to serve a similar but less efficient purpose
I don’t like what AI has done to the software industry but we need to give credit where its due
One canwork in tech and not use LLMs. Your comment sounds like it should be the norm, or already is.
Also, the discussion is about using LLMs in open source projects, which put a lot more focus on understandable and maintainable code than the software industry typically happens to do.
I work in tech and I don’t use LLMs. From my experience, they’re catastrophic especially in those positions where they review code/actions. Reviews are the last line of defense against bad code, bugs, vulnerabilities or destructive actions. Giving that role to an RNG parrot that is often confidently wrong is almost suicidal.
As someone who operates an internal AI code review platform for a large engineering org. Trust me, you want this.
There are countless defects that regularly slip by human review. It’s one of the few places that AI adds immediate, low-risk value.
That aside, though, this is unfortunate. And the author and maintainer of these packages is entirely within their rights to do this as a form of protest.
Absolutionist policies aren’t helpful.
I hate AI and wish it would disappear but you’re right. The automatic PR reviewing LLM at my job genuinely catches a lot of issues that would fly under the radar normally. Obviously a human review is still needed but those downvoting clearly do not work in tech because it’s basically just a fancy SonarQube*
CircleCI (well, apparently they’re AI now but before they did that). If it’s wrong, resolve the issue with one click; if it’s right, then its beneficial?The blanket AI hate is stupid because it drowns out the valid criticisms like energy use, knowledge loss, unmaintainability, etc
edit: I said CircleCI but was thinking of SonarQube
Props for objectively evaluating things regardless of your feelings for them
Not all turkeys voted for christmas
I don’t entirely get the point you’re making but if I’m understanding it correctly my response would be that I’m not pro AI. The issue is that the AI vs not AI conversation always lacks any nuances which means those on the fence just disregard anything being said as just two evangelical bases yelling at each other
We can appreciate the positive aspects of things in tech even if the technology as a whole is a massive problem.
Edit: my point being: can you tell me why PR reviews generated by an LLM are bad? If the discussion was actually diving into the details then I’d be interested but blanket statements are just stupid
See, I don’t agree with this, and that’s why I see it as “stupid” to have a discussion about the nuance of LLM use.
“Damn, the mushroom cloud coming off of that bomb is hella dope tho”, “woah, look at the speed that projectile gets fired at! I didnt even see it hit me”, “actually, those drones can carry water to put out forest fires as well as explosive devices”. etc.
if i have to trust you then doesn’t that kinda show why the technology isn’t particularly useful? Surely it should be able to speak for itself, rather than need you to vehemently insist that “actually it’s really good you guys just don’t get it”.
I’m referring to PR review specifically. Do you not know what PR reviews are?
Sure, maybe it’s fantastic at reviewing PRs. I could imagine that. But
is pretty condescending, implying those against it haven’t thought it through. I personally could list about twenty reasons for not using AI, many of them infinitely more important than code being well reviewed.
Sorry, but what does AI achieve that static code analysis tools don’t? Apart from maybe ridiculous environmental impact?
Having used these at my day job I can understand the policy against them. Ours is fairly well tuned by the people who operate it, adapted to our codebase, and its comments are usually on point, but its false positive rate for my own PRs is still in the low double digit percent range (feedback that’s factually wrong, not relevant to the PR, not scoped appropriately, etc). Before all that tuning, back when we first started using it, I probably went days or weeks without seeing a well-founded suggestion from the tool. Incorrect comments still create work for the PR author (investigating, double checking, etc), they create noise for human reviewers, and ambiguity about whether a change is ready to be merged. I read that policy as being against random people pointing their own review tools at PRs for this project, which I assume would be more on the high false positive/high noise end of the spectrum (i.e., not being tuned for this specific project). I can totally see why already busy maintainers would want to spare themselves from a bunch of poorly calibrated noise.
One nice thing about them compared to human reviewers is that you can just tell them to (professionally) fuck off if they’re wrong without hurting their feelings or having an HR conversation.
I’m not saying you are wrong (not saying you are right either), but… your comment sounds a lot like “trust me, I have a conflict of interest” :)
Trust me, nobody trusts you.
That’s a great way to alienate people who are trying to start discussions. Good job.
Do you have the expertise and experience to state what is or isn’t important for PR change review? The data to back up defect rates and outages?
If not, then you’re just speaking out of your ass and with your emotions instead of with logic.
Do you work in tech? How often do you submit PRs? AI reviews are one of the best applications for the technology and non-LLM CI tools have existed for ages to serve a similar but less efficient purpose
I don’t like what AI has done to the software industry but we need to give credit where its due
One canwork in tech and not use LLMs. Your comment sounds like it should be the norm, or already is.
Also, the discussion is about using LLMs in open source projects, which put a lot more focus on understandable and maintainable code than the software industry typically happens to do.
I work in tech and I don’t use LLMs. From my experience, they’re catastrophic especially in those positions where they review code/actions. Reviews are the last line of defense against bad code, bugs, vulnerabilities or destructive actions. Giving that role to an RNG parrot that is often confidently wrong is almost suicidal.