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

AI PR adds auto generated comments to whole Spring Boot Project

github.com

Post reply on HN
Print view View original

31–40 of 48 posts

Re: AI PR adds auto generated comments to whole Spring Boot Project

#31

Post by ptx »

shadowgovt wrote: post #8

To be honest, I see two positives regarding what Codemaker has provided here. One is that (glancing through the comments) they're actually significantly more thorough than what is already there and they're at the level of thoroughness that a new user may actually want. Phil Webb is quite right; this is the level of detail someone new to the codebase could use, and if you could generate it dynamically on the fly as a…

Do you have an example of those comments you think would be helpful for beginners?

The second point doesn't seem like a positive on the whole, except maybe for the company selling it, in the "there's good money to be made in being part of the problem" sense.

Edit: I noticed one comment that seemed like it added some useful context: For CheckAdditionalSpringConfigurationMetadata.Report::iterator it says "Each line represents a source code file and its associated problems." However, this turns out to be completely wrong, if I'm reading the code right, because a line could represent a filename, or a problem, or just be a blank line. The comment gives the appearance of being helpful while actually just adding confusion and wasting everyone's time.

Re: AI PR adds auto generated comments to whole Spring Boot Project

#32

Post by phyzome »

ugh123 wrote: post #26
Someone1234 wrote: post #24

Comments that say HOW commonly useless, as that is almost always self-evident (i.e. "just read the code."). Comments that explain WHY are worth their weight in gold, and not something AI could ever create. For example: // How: This filters records by MyType of J and if they have children // Why: We want Jobs (J) when those Jobs have Children. Otherwise, we'll get JobGroups or Jobs without any Children we need to proc…

>and not something AI could ever create. Really? You don't think it's a matter of updating the prompt and expanding the context to include more of the code? I don't know the exact method of how they generated these comments, but I think just focusing a prompt on a single method with the entire codebase in context would yield much better results.

"Why" comments typically refer to things outside of the actual code, such as:

* Past incidents

* Regulations

* What the code used to do, and why that was bad

The whole point of a really good comment is that you can't infer it just by looking at the code. That's why it's there at all!

Re: AI PR adds auto generated comments to whole Spring Boot Project

#34

Post by TrianguloY »

Serious questions: for those of you who say "just read the code", don't you find it useful when your IDE autocompletes what a function does? I do. And sometimes you can't even read the code!

Note: I'm not talking about things that you know just by looking at the method itself, but things that are obvious when reading the code of the method only.

    /** This will return the data */
    Data getData() {...}
This is useless, But

    /** This will return true iff it's not empty */
    boolean isValid() {return !empty();}
This is useful. This is what a good documentation should provide, and having documentation in the code itself (that you can later extract to an html page or other) is way better than having it on a separate platform that you need to remember to update.

Edit: remember that this is library that other people will use, it's not an internal tool that only your team knows about.

Re: AI PR adds auto generated comments to whole Spring Boot Project

#35

Post by mjr00 »

TrianguloY wrote: post #34

Serious questions: for those of you who say "just read the code", don't you find it useful when your IDE autocompletes what a function does? I do. And sometimes you can't even read the code! Note: I'm not talking about things that you know just by looking at the method itself, but things that are obvious when reading the code of the method only. /** This will return the data */ Data getData() {...} This is useless, B…

There's often a reason that you want to encapsulate details of the behavior in a library. What if the definition of valid changes in the future and you need to adjust isValid() to also return false if the data matches some other criteria, like being out of bounds? You can say "just change the comment" but the comment is effectively part of your public-facing API and you've just introduced a breaking change.

Re: AI PR adds auto generated comments to whole Spring Boot Project

#36

Post by garblegarble »

cj wrote: post #10

This sort of AI-generated code context seems like it would be better as a VS Code extension rather than in code.

This is exactly my thought on the matter - this sort of auto-generated documentation is transient synthetic data, it doesn't warrant being kept in version control (or, if in version control, in a sidecar db clearly marked as auto-generated)

Always up-to-date and succinct auto-generated LLM-generated 'documentation' that describes a method in terms of who calls it (and perhaps why?) and the behaviour of the whole deep call graph inside the function seems like something that could be quite useful when looking at a method that doesn't have any human written documentation available, and isn't obvious... but it shouldn't masquerade as if it's actual API documentation that describes a durable contract.

If this synthesised analysis could flag incompatibilities between the contract described in API documentation and the actual code behaviour that could be useful (similar to what tools do today for nullable/non-nullable-annotated args/returns, except on fuzzier natural language descriptions of higher level behaviours). That seems like a much harder reasoning problem for the LLM to solve, though.

Re: AI PR adds auto generated comments to whole Spring Boot Project

#37

Post by nameless912 »

ugh123 wrote: post #26
Someone1234 wrote: post #24

Comments that say HOW commonly useless, as that is almost always self-evident (i.e. "just read the code."). Comments that explain WHY are worth their weight in gold, and not something AI could ever create. For example: // How: This filters records by MyType of J and if they have children // Why: We want Jobs (J) when those Jobs have Children. Otherwise, we'll get JobGroups or Jobs without any Children we need to proc…

>and not something AI could ever create. Really? You don't think it's a matter of updating the prompt and expanding the context to include more of the code? I don't know the exact method of how they generated these comments, but I think just focusing a prompt on a single method with the entire codebase in context would yield much better results.

90% of the comments in the codebase on the project I work on now are links to JIRA tickets and incident reports. AI can't and won't ever do that, and those comments are absolute gold. You can immediately read a seemingly less than optimal or overly defensive snippet of code, wonder "what moron wrote this!?" and then immediately read the referenced ticket and realize that it's "overly defensive" due to a caller that abused our API and caused it to fall over.

Re: AI PR adds auto generated comments to whole Spring Boot Project

#38

Post by TrianguloY »

mjr00 wrote: post #35
TrianguloY wrote: post #34

Serious questions: for those of you who say "just read the code", don't you find it useful when your IDE autocompletes what a function does? I do. And sometimes you can't even read the code! Note: I'm not talking about things that you know just by looking at the method itself, but things that are obvious when reading the code of the method only. /** This will return the data */ Data getData() {...} This is useless, B…

There's often a reason that you want to encapsulate details of the behavior in a library. What if the definition of valid changes in the future and you need to adjust isValid() to also return false if the data matches some other criteria, like being out of bounds? You can say "just change the comment" but the comment is effectively part of your public-facing API and you've just introduced a breaking change.

I see you agree with my point. By introducing a breaking change you need to update the facing api, so what better place to not forget to change the api that to place it exactly where the code is!

Re: AI PR adds auto generated comments to whole Spring Boot Project

#39

Post by ptx »

TrianguloY wrote: post #38
mjr00 wrote: post #35

Earlier quoted context omitted.

There's often a reason that you want to encapsulate details of the behavior in a library. What if the definition of valid changes in the future and you need to adjust isValid() to also return false if the data matches some other criteria, like being out of bounds? You can say "just change the comment" but the comment is effectively part of your public-facing API and you've just introduced a breaking change.

I see you agree with my point. By introducing a breaking change you need to update the facing api, so what better place to not forget to change the api that to place it exactly where the code is!

If that documented behavior is part of the API contract, then the entire isValid function seems useless and should probably be removed – if it's intended to check emptiness, just use isEmpty which already does that (or rename isValid to isNotEmpty).

Re: AI PR adds auto generated comments to whole Spring Boot Project

#40

Post by mjr00 »

TrianguloY wrote: post #38
mjr00 wrote: post #35

Earlier quoted context omitted.

There's often a reason that you want to encapsulate details of the behavior in a library. What if the definition of valid changes in the future and you need to adjust isValid() to also return false if the data matches some other criteria, like being out of bounds? You can say "just change the comment" but the comment is effectively part of your public-facing API and you've just introduced a breaking change.

I see you agree with my point. By introducing a breaking change you need to update the facing api, so what better place to not forget to change the api that to place it exactly where the code is!

uh, no, I don't agree with your point. Your example is turning a bugfix into a breaking change by describing the implementation details of a method its documentation, which becomes inaccurate after changing the implementation.

Good developers solve this by not describing the implementation details of functions in comments. This is commonly known as encapsulation.[0] This is why most libraries do not have comments detailing the implementation like you suggest.

[0] https://en.wikipedia.org/wiki/Encapsulation_(computer_progra...

Post reply on HN