cubic

@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

Not getting @cubic_dev_ reviews because Github is down? Use the cubic CLI to run reviews locally: docs.cubic.dev/ide/cli-review

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

@kr0der Use @cubic_dev_ - #1 in every benchmark by a huge margin codereview.withmartian.com

Then @cubic_dev_ Code Review goes through the code and tells the dev what needs fixing

@dominikkoch @greptile just use cubic, only actually good review tool.

@dominikkoch @greptile @cubic_dev_ is best and free for open source

@cubic_dev_ has officially reached "people begging us to pay us" levels of PMF.

Meu dia-a-dia, no momento, fica no @linear plugado no @conductor_build rodando Codex Pro 20x com Claude Code Max 20x. Comecei a usar o @cubic_dev_ para revisar as PRs no lugar do @coderabbitai. Mesclo os modelos por tarefa onde Codex acaba mais no front e revisor do Claude Code.

here is my AI coding stack april 2026 1. Cursor - v3 is the cleanest AI coder out there - super fast, best harness on the market - spending $1-2k/mo and worth every cent - 100% recommend if you can afford it 2. Codex - had a huge relaunch, now my #2 - $200 Pro plan is still insane value - computer use is NEXT LEVEL tech 3. Vercel + Convex for web apps - nothing changed, still the best combo - Vercel for hosting, AI Gateway, analytics - Convex for db, backend, automations 4. Tauri + Swift for desktop apps - still using Tauri/Rust for OpenUsage - played more with Swift (faster but harder) 5. GitHub + Code Reviewers - you MUST use GitHub + reviewers in 2026 - LOVE @cursor_ai's BugBot + @cubic_dev_ - paired with my /shepherd skill = no-brainer 6. Frameworks - still Next.js + Tailwind + Shadcn - this stack never changes, it just works - don't get distracted by tinkerers biggest updates ⤵️ → still not using Claude Code 🤷🏻‍♂️ → dropped Conductor/Superset/other tools → started using @authkit over @clerk and I love it what are you building right now?

We've had an explosion of new users since announcing that cubic (YC X25) ranks #1 in AI code review benchmarks. Feedback is starting to trickle in. I think people like it.

huh, @cubic_dev_'s wiki really cooked with this marketing copy

cubic Launch Week 03, Day 5: AI Coding Analytics AI coding agents write most of the code for your team, but how much of it is AI-written? Which tools and models are your team using? And how good is the generated code? AI Coding Analytics (beta) measures AI coding output across every tool your team uses. Line-level attribution shows what's AI-written, what's human-edited, and whether AI-heavy PRs ship with more or fewer issues. What you’ll get: - Lines of code authored by AI, humans, or mixed (AI and edited by a human). - AI adoption by team member -Tools and models used by your team -Quality of AI-written code: number of bugs, broken down by tool and model You just need the latest cubic CLI installed to start tracking.

@PaulSangleF @cubic_dev_ 5 points in eval land is kinda a lot, annoyingly so

@sumanyu @withmartian 🚆

@cubic_dev_ @withmartian Intense!

We're excited to announce that cubic is once again #1 ranked AI code reviewer on @withmartian 's Code Review Bench. That's 2/2 independent benchmarks where cubic significantly leads.

@mxponential @PaulSangleF 🙏

@PaulSangleF @cubic_dev_ You guys are crushing it

in AI code review, @cubic_dev_ is not just #1. it's pulling away. now we know how much, and it's not even close. the gap from cubic to #2 is bigger than the gap from #2 to #7. - cubic: 56.3% - #2. 51.1% ... - #7. 46.6%