[locusofself]

This is definitely interesting information and I plan to take a deeper look at it.

What a lot of us must be wondering though is:

- how maintainable is the code being outputted

- how much is this newfound productivity saving (costing) on compute, given that we are definitely seeing more code

- how many livesite/security incidents will be caused by AI generated code that hasn't been reviewed properly

[dakshgupta]

We weren’t able to agree on a good way to measure this. Curious - what’s your opinion on code churn as a metric? If code simply persists over some number of months, is that indication it’s good quality code?

[arcwhite]

I've seen code persist a long time because it is unmaintainable gloop that takes forever to understand and nobody is brave enough to rebuild it.

So no, I don't think persistence-through-time is a good metric. Probably better to look at cyclomatic complexity, and maybe for a given code path or module or class hierarchy, how many calls it makes within itself vs to things outside the hierarchy - some measure of how many files you need to jump between to understand it

[refactor_master]

I second the persistence. Some of the most persistent code we own is because it’s untested and poorly written, but managed to become critical infrastructure early on. Most new tests are best-effort black box tests and guesswork, since the creators have left a long time ago.

Of course, feeding the code to an LLM makes it really go to town. And break every test in the process. Then you start babying it to do smaller and smaller changes, but at that point it’s faster to just do it manually.

[nerevarthelame]

You run a company that does AI code review, and you've never devised any metrics to assess the quality of code?

[dakshgupta]

We have ways to approximate our impact on code quality, because we track:

- Change in number of revisions made between open and merge before vs. after greptile

- Percentage of greptile's PR comments that cause the developer to change the flagged lines

Assuming the author is will only change their PR for the better, this tells us if we're impacting quality.

We haven't yet found a way to measure absolute quality, beyond that.

[nluken]

Might be harder to track but what about CFR or some other metric to measure how many bugs are getting through review before versus after the introduction of your product?

You might respond that ultimately, developers need to stay in charge of the review process, but tracking that kind of thing reflects how the product is actually getting used. If you can prove it helps to ship features faster as opposed to just allowing more LOC to get past review (these are not the same thing!) then your product has a much stronger demonstrable value.

[wordpad]

I've seen code entropy as the suggested hueriatic to measure.