TroyBusot

A good family-story question usually starts with one object. The recipe card with a stain on it. The jacket in the hall closet. The watch nobody wears but nobody throws away. Objects are often carrying the story before anyone says it out loud.

Been using Genkit for typescript for about 18 months and love it. Excited for this to come to Flutter/Dart!

This has been in the works for a while. Terribly proud of the team.

@VadimStrizheus Can you use local models?

Anthropic killed OpenClaw.

Am I having a stroke

Back on track and ready to do the Sunday Show. Thanks for the wellwishes!

@AlexFinn Fix your AI auto posts. “1/2 trillion $”??? Come on @AlexFinn ‘s claw.

OpenClaw made Anthropic completely pivot Quite literally every single release the last month has been an answer to OpenClaw • Telegram messaging • Scheduled tasks • Remote sessions A 1 person led open project caused a 1/2 trillion $ company to completely change everything You have way more power as an individual than you think

Every family has stories that live in fragments. a remembered phrase a kitchen ritual one photo with no caption the story behind a name Iloomi exists to help families turn those fragments into stories worth keeping. We’re here for memory, voice, family history, and the questions that unlock a life.

@dneighbors @RobW16856727 @TechLayoffLover Opus 4.6 was the first model that yielded real results for us. Noticeable acceleration and quality. Less rework. Increase in cognition. The biggest gains we are seeing is with Cowork and coordination/project management. I think the story represents a good hypothetical.

@RobW16856727 @TroyBusot @TechLayoffLover Things have been fairly usable since GPT 4 (3 years ago) but became practical in early 2025 with orchestration tools like BMAD. Precursor specialized agents, skills and plan mode.

A director of engineering at a major cloud platform just messaged me about something that's keeping her up at night Last September she got the call: "We need you to optimize your team for the AI era. Cut your 12-person backend team down to 3. Use Copilot, Claude, whatever it takes. Same deliverables expected" She did it. Laid off 9 engineers she'd hired herself. Kept her 3 strongest seniors and armed them with every AI tool in existence Her team's velocity actually increased 40%. Deploy frequency went from twice weekly to daily. Bug rates dropped 23% because the AI caught edge cases humans missed Got promoted to VP Engineering in February. Glowing performance review. "Exceptional leadership during digital transformation" Yesterday she got a calendar invite. Same conference room. Same two VPs who congratulated her 6 months ago "We've been analyzing our engineering leadership structure. With AI handling more architectural decisions and our offshore partnerships scaling up, we need fewer management layers" Her role is being "consolidated" with two other VP positions. One person will manage what used to require three The meeting ended with them asking her to document all her processes, decision-making frameworks, and team management strategies "for knowledge transfer" She's building the playbook for whoever replaces her. Probably someone offshore making 1/4 of her $280k salary The best part: they want her to train her replacement on "AI-enhanced leadership methodologies" She optimized herself right out of existence

@steipete Been using QMD all week and the results have been quite good.

There's a lot of cool stuff being built around openclaw. If the stock memory feature isn't great for you, check out the qmd memory plugin! If you are annoyed that your crustacean is forgetful after compaction, give github.com/martian-engine… a try!

@GeraldMorrison @cgtwts Throw in Activepieces for local configurable MCP and 64gb to run local models where needed. Agree 💯- I’ll be buying more, not fewer minis.

@cgtwts “Paid Partnership”. It’s $200 a month with rate limits and who knows where it’s hosted or how secure the back end is. RIP a $600 Mac Mini? You can buy a Mac Mini every three months give the cost of this service.

RIP to everyone who just bought a $600 Mac Mini Base44 just dropped Superagent. > persistent memory > scheduled jobs > event triggers > browser sessions It’s basically an agent that runs your workflows on autopilot and is very simple to use.

@ErickSky @elonmusk You’ve used Grok, right? No thanks.

🚨 ¡SI COMPRASTE UN MAC MINI PARA TU OPENCLAW… ESTE POST ES TU SEÑAL PARA VENDERLO YA MISMO! @elonmusk acaba de perder ABSOLUTAMENTE LA CABEZA con este anuncio y acaba de hacer que tu Mac Mini de $1500+ valga… menos que un ladrillo de un rancho en Petare. Acaba de anunciar MACROHARD (Digital Optimus): el proyecto bomba conjunto xAI + Tesla que va a volver mierda el mundillo IA. ¿Por qué vender tu Mac Mini HOY? Porque el nuevo hardware que Elon acaba de revelar es 10 veces más barato y 100 veces más bestia para IA real: ✅ Tesla AI4 → el cerebro rápido (System 1) - Solo $650 (sí, SEISCIENTOS CINCUENTA DÓLARES). - Chip diseñado por Tesla (y ayudadita de NVIDIA), fabricado en masa, consumo ridículamente bajo. - Ve los últimos 5 segundos de tu pantalla en tiempo real + controla mouse y teclado como si nada. ✅ Powered by Grok (xAI) → el cerebro que piensa de verdad (System 2) - Uso mínimo de los GPUs Nvidia caros. - @grok dirige TODO como un GPS hiperinteligente. - Puede emular el funcionamiento de empresas ENTERAS (por eso lo llaman Macrohard, en referencia a los juegos RTS como StarCraft, LOL, AOE...). Resultado: un monstruo que corre en hardware Tesla barato y hace que tu Mac Mini parezca un juguete de los 90's. Es que seamos claros, esta es una IA que estaciona cohetes espaciales para que sean reutilizables versus el resto que aún no sabe hacer un SAAS multimillonario con un solo prompt make no mistakes. Está desbalanceada la pelea. El futuro no es un ordenador bonito… es un agente IA de $650 que trabaja por ti 24/7 amigo, entiende por favor.

@THErealDVORAK praying hard for you, sir! Focusing all of my Lenten powers to you.

@SotDPodcast The pool boy! Fun fact - in his career at ASU, he never had a run for negative yards.

Name a random ASU running back. Tom Pace

@PhilippHGerber Always prefer named for readability and future-proofing refactors.

❓ Question for the #Flutter community I'm adding "Widget Interpolation" to 📦 Textf (inserting Widgets directly into styled text). Which placeholders API do you prefer? 1️⃣ Positional: {0} (List) 2️⃣ Named: {icon} (Map) Drop your reasoning below! 👇 #Flutter #Dart

@JesterJum Yep. 💯 and the kids are stronger for it.

Did you know previous generations held "chicken pox parties"? Where if one kid got the pox, they would get all the kids together for a party so it spread and they all got it. To "get it out of the way". That is absolutely insane to me and borderline child abuse.

@nicksortor @AliBradleyTV You mean they don’t lear.

🚨 JUST IN: An old white liberal lesbian chucked a water bottle at agents outside ICE Minneapolis, and then attempted to run away But she didn’t get far, as agents SPRINTED after her and brought her to the ground These idiots don’t learn😆 @AliBradleyTV

@Commit2theFork OL

What position group would you like to see ASU fill next in the portal? 🔱🆙

@PhilippHGerber This looks VERY promising. Will be checking this out for iloomi this week.

🚀 Textf v1.0 is live! Effortless inline formatting for #Flutter. ✅ Zero dependencies. ✅ Blazing fast (+0.06ms vs raw Text) ✅ Fully customizable. 👇 What you write vs. What you get: