Amart (LOOP)⚡️

Founder and Managing Partner Edge AI | prev @Rivian | I show you how to transform your life with AI @umich

[Amart (LOOP)⚡️ @LoopOnChain]

https://t.co/RYgvyMO2Y7

[Amart (LOOP)⚡️ @LoopOnChain]

@zebulgar @rabois highly recommend looking into something like gbrain for a long term memory system

as you work the data compounds and you get much better suggestions on how to spend your time

[Amart (LOOP)⚡️ @LoopOnChain]

I think mass firings feigned as AI revolutions are getting ridiculous

2 people who are great with AI are better than 1

and if you’re business can’t scale that’s a leadership problem

seems to be an excuse to fire bad performers (or maybe a peer pressure, all my ceo friends are doing it so my board expects me to)

[Amart (LOOP)⚡️ @LoopOnChain]

You’re firing 22% but you say the future is not less people?

Meaning you’re going to hire different (better?) people to do jobs?

Why not just train your existing workforce who already understand the context of your business and supercharge them with AI?

Fire bad performers always, but if 22% of the org are bad performers maybe you’re not hiring well?

Genuine questions here

[Amart (LOOP)⚡️ @LoopOnChain]

@bwarrn super cool, going to try it out with my agent

[Amart (LOOP)⚡️ @LoopOnChain]

@businessbarista @tenex_labs feels like it could be a “claude do this” task, no?

maybe i’m missing something

[Amart (LOOP)⚡️ @LoopOnChain]

@trillhause_ respectfully disagree

my favorite tools are ai that scrape a companies date and builds a system custom based on their current system

[Amart (LOOP)⚡️ @LoopOnChain]

@ml_angelopoulos a couple months?

[Frank Y @frankekn]

Simply Lovely !

[Amart (LOOP)⚡️ @LoopOnChain]

I do AI implementation at startups + large companies

one is an M&A firm, the 50+ year olds absolutely HATE ai

like really hate it

I show them they can turn the annoying manual spreadsheet process they've been doing for 10 years into to 1 skill

/skill + enter

then it's done

they change their minds pretty quickly

[Amart (LOOP)⚡️ @LoopOnChain]

.@steipete GPT 5.5 with openclaw is simply magic

incredible work 🦞

[Amart (LOOP)⚡️ @LoopOnChain]

@vincent_koc @douglasfugazi some of these questions really make me laugh

[Amart (LOOP)⚡️ @LoopOnChain]

@thsottiaux i was at 2% bless up

[Amart (LOOP)⚡️ @LoopOnChain]

@steipete @allanmelsen HAHA this is a great response

obviously op has good intentions but this is great

[Amart (LOOP)⚡️ @LoopOnChain]

@fxnction @openclaw use github, make sure they work in separate project folders, then use a CEO agent to manage them

if working in the same project, have them take the “lock” so it shows the other agents which code they’re working on

[Amart (LOOP)⚡️ @LoopOnChain]

@Voxyz_ai yeah significantly better, can also run claude via ACP sessions which works great

[Amart (LOOP)⚡️ @LoopOnChain]

@hunvreus ai will tell them not to hire you for this tweet

[Amart (LOOP)⚡️ @LoopOnChain]

@KingBootoshi very helpful when it becomes a system or skill you can just call and have it go for 4 hours and build something flawless

anything you’ve found particularly helpful or hurtful in your prompting/ skill making

[Amart (LOOP)⚡️ @LoopOnChain]

@doodlestein there it is 🔥

[Amart (LOOP)⚡️ @LoopOnChain]

@pashmerepat Seems like we need to set codex as the default embedded harness

[Amart (LOOP)⚡️ @LoopOnChain]

@pashmerepat Do we need to tell our agents to start using codex as the default harness or is this automatic when using the open ai codex oauth?