tech mumus

Canal do YouTube sobre tecnologia e inteligência artificial

[Santiago @svpino]

Humans have an average of 200-250 ms of latency when speaking to each other.

This voice model is even faster: only 110 ms of latency!

Open-weights ←You don't need to pay anyone to use it.
8B parameters ← Small and cheap to host and run.

You can run it locally by cloning the Github repository. They published the instructions in the repository below.

Open models keep getting stronger!

[tech mumus @techmumus]

@leonardogrig Thanks for sharing!

[tech mumus @techmumus]

@leonardogrig Why??? 😳

[Mike Rundle @flyosity]

--dangerously-skip-permissions

[tech mumus @techmumus]

@leonardogrig @firecrawl 100% agree. People focus on cool demos, but this is the stuff that actually compounds in real projects: monitor, detect changes, trigger action. Quietly becomes a serious moat over time.

[tech mumus @techmumus]

@br_aiengineer Love this take. The compounding edge shows up when teams pair automation with tight eval loops (quality, latency, and cost budgets). That’s how AI workflows become real business systems, not just demos.

[tech mumus @techmumus]

https://t.co/WcT7tBoxpp

[tech mumus @techmumus]

Airlines have a secret: the flight price you see depends on YOUR location.

So I built a Python script, powered by @thordata, that pretends to be in 8 countries at once to find the
cheapest fare.

Watch how it works and grab the script for FREE! ✈️💰

[tech mumus @techmumus]

@leonardogrig Poor quality?

[tech mumus @techmumus]

Wanna try? One-click deployment on Railway
https://t.co/xPMc2Cnkms

[tech mumus @techmumus]

Super proud of getting the 3rd place in the Railway Hackathon!! Thanks @railway for the opportunity!!

[Railway @Railway]

Content Depth 3️⃣ 3rd place:

Mosaic, a knowledge management system (https://t.co/ErRM8RIJbf)

[tech mumus @techmumus]

@leonardogrig Tried, but didn’t get much traction here. It seems that long-form videos don’t match the audience’s focus. I saw @svpino posting some nice videos here, probably a good person to provide some insight.

[tech mumus @techmumus]

Amazing work @JNYBGR your tool now has a huge advantage with AI!

[tech mumus @techmumus]

Create amazing videos using plain english and @Remotion and Claude Code @claude

[tech mumus @techmumus]

https://t.co/nENJWhFFmb

[tech mumus @techmumus]

🧠 Just shipped MOS•AI•C - an AI-powered knowledge management system that actually understands your notes!

Deploy in one click on @Railway: https://t.co/xPMc2CnSc0

[br_aiengineer @br_aiengineer]

🚀 AgentTip: OpenAI assistants inside any Mac app.

Type @idea brainstorm an onboarding flow, hit ⏎, and AgentTip swaps the trigger for the assistant’s reply—right where you were typing. No context-switch, no copy-paste.

One-time payment $4.99.
#MacApps #ChatGPT #AIProductivity

[br_aiengineer @br_aiengineer]

The era of AI app subscriptions is coming to an end…
Thanks to the advent of lightweight edge AI models and frameworks like cactus - developed by @RomanShemet (backed by @ycombinator) AI apps can run 100% on the phone

My offline Plant ID app is proof:
👉 https://t.co/uhvofRcX6O

No more cloud fees. No more monthly charges.
Just fast, private, one-time apps.

[Matthew Berman @MatthewBerman]

I've spent 200+ hours Vibe Coding games and apps.

It's insane what you can build with just your voice and AI...ANYONE can do it.

Here's everything I learned about Vibe Coding: 🧵

[tech mumus @techmumus]

https://t.co/vx8RUV7rGH

[tech mumus @techmumus]

That's amazing! New Playwright MCP Server, controls the browser, open countless doors! Thanks Debbie and Playwright team!
In this video we implement it in Cursor analysing a platform like Amazon (Mercado Livre)
@playwrightweb @debs_obrien