Ron Northrip

Hey #laravel friends. Anyone going to @LaraconUS want to get together for a little jam session on day zero? Give me your feedback here in this poll so we can put together a plan.

A tale as old as time 🤣

my theory on boomer ceos being opposed to remote work is they simply don't like their families

We're slowly entering a new chatper: Self-hosting AI models is no longer all-or-nothing. There is now a real middle ground between toy-setups and getting serious work done! Here's the practical breakdown 👇 → Qwen3.6-27B 30.5B total params. 3.3B active. 262K context. Runs in the sane range: ~$0.70/hr on Vast AI with an 80GB-class GPU. This is the practical entry point for agent work: Research, sorting, docs, support prep, and simple tool workflows. Small enough to run without doing anything ridiculous. Large enough to be worth taking seriously. → GLM-5.1 235B total params. 22B active. 256K context. Now you're in multi-GPU territory: ~$3-6/hr on Vast AI depending on setup and context. This is where self-hosting starts to hurt a bit. But for higher-value internal workflows, a few dollars per hour is not crazy if the agent can stay coherent, use tools properly, and finish more work without constant correction. → Kimi K2.6 744B total params. 40B active. This is the high-end setup: ~$12-20/hr on Vast AI with serious multi-H100 infrastructure. Not the normal founder setup. But useful as the upper edge of what open-weight agentic models can look like when you stop pretending everything has to run on cheap hardware. It's a tough balance right now! We want agents that can use tools, keep context, handle files/APIs, and finish actual work. But we don't want OpenAI and Antrophic to own us forever.

@pushpak1300 @rustlang Vite too

codex and claude code both betting on @rustlang means something.

AI absolutely makes it easier to build software. But as @mattstauffer points out: the hard part was never just shipping v1. It’s the six months later: the integrations, the edge cases, the maintenance, the “oh… this feature is actually complicated.” share.transistor.fm/s/15e406dd

Laravel AI SDK now supports sub-agents. 🤝 Return an agent from another agent’s tools() method and the parent agent can delegate focused tasks to it, just like any other tool. Sub-agents can have their own instructions, tools, provider config, and isolated context. #sub-agents" target="_blank" rel="nofollow noopener">laravel.com/docs/13.x/ai-s…

Do I know any Laravel devs near Boston? A new Laravel meetup starts up this week! meetup.com/boston-laravel…

Ship it!

@avosalmon @enunomaduro @LaravelLiveJP 🙌

Just 2 weeks until @LaravelLiveJP 🇯🇵 Last week, we had an on-site meeting at the venue and stood on the actual stage. In just two weeks, this place will be filled with 500+ artisans from 40+ countries. Still hard to believe. We’re almost there. Can’t wait to meet everyone 🚀

What can PHP do? Anything! Great video @brendt_gd 👏🏼

@aarondfrancis Man I miss those days. We only had the one. But there is so much joy! Ours is now graduating high school and going to trinity college in Dublin this fall!

@aarondfrancis 🤣

Happy pizza and stomp rocket day to all who celebrate

Hello all you lovely @laravelphp and #buildinpublic friends. Hope you have a great Friday. Only 80 days to @LaraconUS Hope you see you in Boston!

@enunomaduro @laravelphp Have a great conference!

hypeeeeee 🔥@laravelphp

@ericlbarnes @mattstauffer Mine has a gluten allergy. I feel you.

@mattstauffer My daughter is allergic to garlic, so we can't eat anything. 🧛

Usually at least 3 to 4 times whatever the recipe calls for lol if it’s savory, it should have garlic on it. I’ve never yet hit the point where I say “this is too much garlic”

Coming up this month at KYPHPUG:

@taylorotwell Nice

With the Laravel AI SDK, any string can `->toAudio()`. 🗣️

/upgrade + Shift = "fully upgraded"