Founder, AutonoMax Innovations. Building @CoRoamApp, AI agents, and useful software. Tech, fitness, philosophy.
Joined May 2026
- Tweets1.5K
- Following165
- Followers209
- Likes1.6K
One of my favorite things about @CoRoamApp is building my atlas.
Seeing where I’ve roamed and picking new spots I want to explore was something worth building 🌎 🚶♂️
For a wall-mounted home screen, voice has to do most of the work. If I'm standing in the hallway typing on a tiny keyboard, I'll just use my phone.
Built a small @expo + @supabase starter for when a photo uploads but the app thinks it failed.
It keeps the photo on your phone and checks what's already saved before retrying, even after a restart.
Code's on GitHub if you want to try it:
github.com/maxgorriaran/expo…
Build a body you're proud of and a bulletproof mind to power it.
The goal is to feel capable of taking on anything, and build the strength and discipline to back that belief up.
Microsoft’s approach here is interesting: combine models from different labs with specialists like Decision-1, then put them to work across software businesses already use.
Curious how far that goes inside Copilot.
Introducing Microsoft-Decision-1, our new model for fast decision-making.
It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality.
We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.
The U.S. executive branch is switching from AI to SI: Super Intelligence.
Curious if that name catches on, and how long it takes.
It puts a much bigger expectation on what these systems should actually do.
OpenAI has released math research generated by an internal AI model for others to review.
That’s an interesting benchmark: can AI help us figure out something we didn’t already know?
openai.com/index/sharing-ai-…
You can test a walking app from your desk by making a virtual iPhone follow a route.
One Apple command moves it at 72 km/h (45 mph) by default.
Maybe a little ambitious for a walk. Set it closer to 5 km/h (3 mph).
A walking app should give me a reason to look up from my phone.
@CoRoamApp points out the interesting street or the view I would’ve walked past, then lets me enjoy the walk.
Affordability is winning.
Anthropic says Haiku 5.5 costs around 75% less to run than 4.5. When agents make dozens of calls per task, that changes what’s worth automating.
I think cheap, capable models become the default.
If AI helps an employee finish an eight hour task in two, who gets the other six hours?
The company paid for the tools. The employee figured out how to use them.
How should they split the benefit?
My bet: model routing becomes a core feature of AI tools.
Let me set the rules for which models run, when to use a pricier one, and how much the agent can spend.
I’m fine paying for useful work. Show me where the money went.
