Whatever @cubic_dev_ has been cooking, it's legit. 3 reviews in and I already got WAY more issues pointed out than with built-in Codex/Claude reviewing
@PaulSangleF@aaronmahlke@cubic_dev_ local review is not only a great workflow win, but also great for #finops - find issues before they hit full CI!
We use it for great benefit since it became available in #rsyslog. And it improves PR quality dramatically.
@catalinmpit I use @cubic_dev_ for a while now (both for open source project and proprietary one). Pretty efficient, we tested alongside Codex/Claude/Copilot reviews etc ... and this is a no match.
@jonahseguin@PaulSangleF That shouldn't happen and it's on us.
We've already shipped a fix and are doing a full sweep to make sure nothing else is affected. Appreciate you raising this so quickly.
@jonahseguin@PaulSangleF Thanks for flagging this, Jonah. We take this seriously and here's what we found.
No private repo contents were ever accessible. The issue was that repo names from orgs where you'd been added as an external collaborator were incorrectly showing up in your cubic UI.
@asaio87 I use a stacked diff workflow, so small PR slices that stack on each other. Easier to setup a review process. This allows me to do quick manual reviews, and I also utilize @cubic_dev_ for automated reviews.
One thing that I love about @cubic_dev_ is the: "Prompt for AI agents" option where you can copy a prompt that is generated for you, copy/paste to your LLM of choice, so good
@robinebers I just started using @cubic_dev_ when I first see your suggestion and man, same feeling over here it is so fast compare to bugbot, also I like the information and the dashboard
starting to love @cubic_dev_ more than cursor's bugbot
every time I run PRs, cubic is just as good
at literally half the time it takes for the review
that's my biggest issue with bugbot - how extremely slow it is
starting to believe this will never change because it's all-inclusive and using e.g. GPT 5.5 FAST variants would cost 2.5x more while we pay the same
recommending cubic to most people now for speed
@withmartian jump in!
There’s only 2 independent benchmarks for code reviews.
One of the benchmarks is an online benchmark that measures performance live across tens of thousands of open source PRs.
The other benchmark is an offline one, where the lab maintains a data set of ADPRs with known bugs and runs all the code review bots on them.
@cubic_dev_ is first in both, by a huge margin