If you think there are less opportunities now that we have powerful AI, think again. I have to stop myself from accidentally creating new businesses. There are literally opportunities all around us. Most of it, very low hanging fruit. Just find someone and help them.
Real world story, my $200/month Claude Max subscription has more then paid for itself in real world business expenses. I used it to rewrite my backend code running my maintenance server to Go, offloaded a bunch of storage to B2 and reduce my Oracle Cloud instance by $400/month.
@ryancarson Handles WordPress migrations over SSH very smoothly. Even what I call the true test, extract a subsite from a WordPress multisite. https://t.co/YaNOPXgG5h
The true test of any AI model, can it extract a subsite from a multisite network. Trying out Gemini 3.5 Flash.
> I spun up a new empty WordPress site here: ***. SSH info: ***. Extract the subsite *** from the current multisite network and import as a standard site over to ***?
Keeping all your plugins updated is not always obvious. For example: the popular eventON plugin originally purchased from CodeCanyon only goes up to 5.0.6. If you want the latest 5.0.10 you need to migrate your license to plugin authors own system. #plugin_updates
@jeffr0 The ability to patch your own plugins has never been more accessible, thanks to AI. I recommend everyone have Claude Code run a security audit and patch for all themes and plugins on your site. Report any critical findings to appropriate channels.
@ChanningAllen@caps_raunak Agreed. We all have access to these powerful AI models. Not everything the tool produces will come with high praise. It’s still the creativity of the individual behind the tool that matters most.
@photomatt@gauravsapkotanp@wordpressdotcom Honest feedback: https://t.co/qnfaZQc7nd login is slow, maybe show a dashboard rather than the full list of sites? On domains, add an export DNS button. Add an API for managing domains.
BIG day for us!!
@CommandCodeAI has crossed $1M in annual run rate, 1 trillion tokens of usage, with over 9K customers, just 24 days after our public beta launch.
we believe this makes it the fastest-growing coding agent harness for open models. 3rd largest by usage.
Command Code is built around two ideas:
1. open models should be production-grade for coding.
2. your coding agent should learn your taste.
we're building for taste and developer experience. so instead of making a soup of thousands of models, we build for the best ones, open or closed. the goal: a coding agent that feels like an iphone, opinionated and with taste, not a random android or a windows phone with no taste.
on the first idea: open models.
we fixed the "open models aren't good enough at tool calling" problem. our research came down to two things, quality and speed, and both trace back to one root cause: broken tool-calls that open models produce, especially when you use a bad harness.
open-model tool-call failures are not deep, they are a small finite set of contract mismatches. so we repair them, with zero token loss. what started as 4 repairs is now the largest repair layer in the space: 36k tool-call fix variants. i wrote the idea up openly¹ a few weeks ago, and it has quietly become a de facto way people fix open models.
developers have either adopted Command Code or used the same idea to build repair harnesses for nearly every top coding agent. i take that as more meaningful validation than anything we could say about ourselves.
on the second idea: taste.
Command Code builds your coding taste into skills, learned from your accepts, rejects, edits, prompts, and the corrections you repeat. over time it drifts away from generic code and toward how you actually ship code. it learns continuously, and while it is early, the direction feels right.
net effect: developers using Command are writing production-quality code on open models, 10x to 100x cheaper, without fighting tool calls, while building repo and team-wide coding taste that compounds.
i believe these numbers are a consequence of getting those two things right.
what's next.
we've applied the same repair idea to ai design slop, and bundled a /design capability² so every developer can level up their design work. the early response has been great.
we have a big roadmap ahead of us. the feedback we hear most is that Command Code feels fundamentally different: an approach built on taste and repair.
we're going open source next month. today we're a cli at the core, and we're also launching a full-fledged gui app, sandboxed background agents, and cooking up something fun i can't wait to share.
we're growing too, hiring in sf and remote worldwide. check open roles on my profile bio.
try it now.
npm i -g command-code
if you like engineering deep dives on how we're doing all this, i've linked some relevant posts below.
@jjstyler@austinginder Thanks for trying to help. But I have not heard anything from GoDaddy. Just emails from generic accounts that said everything was done correctly. Working at getting some lawyers involved to issue a subpoena.
A month later my security report via HackerOne was closed saying it's a support issue. Fair enough but if support has been unwilling to dig in, isn't that a security issue?
Last week GoDaddy moved a 27-year-old domain from my friend's account to a stranger who never submitted a single document. They used an email signature to identify the parent domain and just transferred it. Here's the full story: https://t.co/L1vNJ64l9s
@dannyvankooten Yep I’ve been using Caddy for many years on my local dev. Since Cove is a CLI it’s very easy for an AI agent to manage. Indeed… it’s a Claude Design.