When a nerd tells me they don't use agents "because I can write better code than any agent", I usually go "huh, sure buddy, you do you". When they tell they don't use agents for monitoring, I just laugh in their face. Seriously. You can't monitor a production deploy better than an agent can. I dunno about AGI but this specific job is something that an LLM can already do better than every single human in the world. For me, as a systems engineer, having agents monitor my infra changes has been (no joke) more impactful in my day-to-day work than having agents write my code. I started doing this many months ago by asking the agent to monitor explicitly after I triggered a deploy; soon after I moved to using a set of my own Skills. Now our Review Agents team has fully automated this workflow with delightful UX and obviously I'm not going back. It's hard to overstate how powerful this is. All it takes, for me, in production: - The Datadog MCP - The PlanetScale MCP (for all our databases) - Our custom MCP for deploys and internal tooling That's it. Some carefully designed gradual deploy pipelines, and the agent just takes care of everything from there. You can't really deploy SEVs to production anymore. Doing infra like this is pure joy. And the safety is just a tiny part of it. The Rollout agent also does the actually hard part of my job, which is _performance_. When the changes you're deploying are a performance optimization, the agent prepares a monitoring plan that ensures the optimization is correct AND effective. I rarely prompt benchmarks for my optimizations anymore. Just fucking go to prod and the agent is gonna give me the best possible benchmark. If you work on systems or infra for a living, you should be setting up your production environments so you can use Rollouts. Not doing so is actually reckless.

Grok 4.7 is here. It's a notable improvement over Grok 4.6 at the same price and speed.

This is nothing. There's no frontier AI development in this country. The very few Spanish engineers working on frontier AI are working for American companies. It is literally impossible to develop competitive AI in the socialist hellscape that this guy has thrust upon us.

Congratulations to the PlanetScale team on this massive ship! This is a seismic shift in scalability for the Postgres ecosystem. I've been playing with Neki and every other approach to scaling Postgres that came before it feels like a toy in comparison.

Two of the founders I admire most, @tobi from Shopify and @chacon from GitButler/GitHub have spent their weekend doing two implementations of the design of Origin's git storage layer I published last week. They're both functional already! Just another demonstration that all founders are not the same. These fucking nerds have more money than God and whole-ass companies to run and they spend their spare time re-implementing papers for fun. Bullish as fuck.

Thanks to everyone who read and enjoyed this post. I'm humbled by the reception it's had. I really mean what I wrote in the last section: this is a problem space we deeply care about and we're really committed to delivering. If you work at a small/medium/Enterprise company and are struggling with scale or availability, come chat with us. We'll show you the roadmap, you can stress test, kick the tires... I'm stoked to hop on calls and answer your technical or migration questions. I'm vmg at cursor dot com (or just DM me).

Seriously though, this is how I usually do these blog posts: I write down and edit a pretty final version of the post by hand, and leave placeholders that explain what the visualization should look like. Then I just pass it on to Grok 4.6 and let it cook! I used to use Fable for visualizations (e.g. in the Indexed Grep blog post), which also does a very good job at interactive SVGs, but it had the very bad habit of going "I did your visualization and AKSHUALLY also fixed some of your English grammar because it seemed off". ffffffffffuu please dont fucking do that. After testing 4.6 here and looking at the quality of the viz and how well it follows instructions (i.e. leaves my text alone, tyvm), I'm not going back!

Good news @grok, you're getting a hug _and_ a raise from Adrián! I'm not sure of what that means in practice. Maybe we'll just feed you a few more GPUs. I'll keep one as your humble prompter and use it to play videogames I guess.

I did a write-up of things I learned during my 10-year tenure at GitHub, the things that worked, and what we're trying to improve in Origin. The scale of the challenge is staggering, but I really want people to know we're putting a lot of thought and care into it.

Cool ship for my first day at SpaceXAI. I'm stoked to be working on Git infrastructure again! I think everybody is now very aware of how hard it is to do this stuff at the scale that agents require. Can't wait to blog about our design and operational philosophy for the platform

Ideas para alguien que esté acabando la carrera y quiera una internship bien en Españita? (el primero que diga Indra saco la escopeta)

This is a major breakthrough in both intelligence and cost efficiency. The team really outdid themselves! Sadly it’s a large enough model that it cannot ship in the EU right away, but it’s coming very soon.

Composer 2.5 is now available inside Grok Build. Composer 2.5 is a fast, highly intelligent model that excels on long-running tasks and following complex instructions.

He also did this one when I was the maintainer of libgit2. He's very good at this!

Banger blog post from the Turbopuffer team. Great breakdown, great interactive visualization and obviously a great implementation like they always do.

We've been developing a multi-agent system that builds and maintains complex software autonomously. Recently, we partnered with NVIDIA to apply it to optimizing CUDA kernels. In 3 weeks, it delivered a 38% geomean speedup across 235 problems.

I've just dropped a Mirror of Kalandra playing Path of Exile. That's... an extremely uncommon thing.