Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run.
This beats any paid course on agents I've seen.
Watch it, then read the guide on building loops below.
Been building a retro pixel-art platformer with Flutter + Flame in my spare
time 🎮
50+ levels, full level select, launching soon on iOS and Android.
Join the waitlist if you want to know the second it drops. 👇
https://t.co/BAB0uIwDSR
#Flutter#GameDev#BuildInPublic
Open sourcing it today, code + the 99-clip labeled dataset:
🔗 https://t.co/4XhehlxyM4
🔗 https://t.co/qKmoPkNE66
If you work in ML/audio/telecom, fork it and make it sharper. #OpenSource#MachineLearning
Most predictive maintenance tools assume you have vibration sensors, a smartphone, and internet. We built one that assumes none of that.
Machine Sound Doctor: Call a number, hold your phone near a running machine, and get a text back diagnosing normal / bearing fault / belt slip
I built a voice assistant that runs 100% locally on my Mac—no cloud, no
API keys, no subscriptions. Say "Hey Jarvis," and it converses, remembers
context, and can act for you (read/write files, run commands, open apps,
search the web)