@mikkmartin you don't need better diff review, you need better risk analysis -- risk: low gets automerged, risk > low gets increasingly more intelligent automatic reviews, risk critical has an agent work on it to split it up and de-risk so only the critical changes get a human review
@bearzk@lexrus give your agents the tools to verify their output, you make sure the expectations are clear and they'll do a great job nearly every time
and where they don't make them file a follow-up ticket to fix it
Built for 80,000 connections, December in Buffalo, and loud fourth quarters. The new Highmark Stadium runs networking and security on one @Cisco platform. Love to see it. Keep rolling, @JoshAllenQB and @BuffaloBills! https://t.co/7mvAbK40vg
You don't need a software factory. You need an abstract software factory provider which can instantiate concrete software factories without coupling the client to a specific software factory implementation. Have some fucking self-respect.
@mattpocockuk how can you treat this like a hypothesis and test it? I'd completely disagree that understanding react is valuable at all, but how could we prove it either way?
@kentcdodds I'm not convinced these generic solutions will ever work. In a world where 100% custom solutions are cheap and easy to build, these one-size-fits-all solutions feel like a huge step backwards.
I'd love to draw inspiration from what you've done, but wouldn't use it myself
@mattpocockuk this is how I'm building my factory, we need an always-on intelligence to nudge things and do housekeeping, and bring HITL when absolutely needed
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!