Mike Jar

I made a mistake with how I talk about T3 Code. A lot of people seem to think it's a product we sell with subscriptions. I get why - that's how T3 Chat works. Want to make it clear that we CAN NOT MAKE MONEY ON T3 CODE RN. You HAVE to bring inference from somewhere else. Codex, Claude Code, Cursor, and OpenCode are all supported, with many more coming in the future. Just shipped an overhaul of the landing page to emphasize this point. You bring your inference, your subs, your harnesses, whatever you use, and we give you a better interface :)

@KaiXCreator Convex.

Which database are you using for your product? -Firebase -Postgres -MongoDB -Supabase

@AliGrids @staromlynski wow. yeah. super impressive. clean AF

This UI feels expensive. by @staromlynski

/grill-me is my most popular skill ever. I get 5-10 messages a day about how it’s changed people’s workflows for the better But… I’ve stopped using it for code. Here’s the improved version:

I just earned the Explorer badge in TanStack Island Explorer! ⭐ Discovered all the TanStack libraries! tanstack.com/explore

@Jason shit. I'm boycotting almonds... for exactly 3 days only

Honestly, fuck almonds

@brockpierson alright, let's move out

If you know what this is then you are totally cool with me

@KaiXCreator driving

If AI builds everything for you, what’s your real job?

@Tekeee lmao, right

Small accounts posting into absolute silence

want this? Discord notifications from your YouTube channel Live scheduled, Live started, Video posted, all separated! Add a role per event type. Check it out, TubeHook.app

@KingBootoshi fkin banger

all a company needs is an autistic nerd with adhd and a $200 codex subscription

@HermesAgentTips keep going!

I started posting consistently 4 months ago with almost no traction but I never gave up Kept going, kept trying I was very passionate about AI, LLMs and AI agents so it didn’t feel like work Today my account has blown up 🔥 Thank you for so much love ❤️

@threejs um. yes please

@bryan_johnson lmao wtf did I just watch. loved it

can you get a perfect score?

@knowRowan 24gb I think is baseline. up from there is good

Looking to get a system for running AI locally, how much VRAM will i need in my GPU ideally? -4GB -8GB -16GB -24GB -32GB -64GB

@theo lmao

“Fast and flicker-free” shots fired directly at Anthropic

@RoundtableSpace TCG Card scanning automater

WHAT ARE YOU BUILDING TODAY?

@davepl1968 fkin ultra cool

After getting UNIX running on my tiny PDP-11, I decided to make it even smaller, this time on a watch. It's fully emulating a DEC PDP-11/73 with DEUNA ethernet, RA92 disc packs, and basically everything else that used to fill a data center!