Anthropic Research Lead:
"99% of our engineers run swarms of 300+ self-improving agents"
"Close the loop, give the model a way to verify its own output"
In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves
The real setup is Claude running through loops, plan mode, and dynamic workflows
Better than most $300 agent courses
Bookmark and watch the talk
Then read the article below
Introducing Runbuds - a Strava competitor.
For the past 6 months @rafsoh, @drqas, @gabfoulon, and I have been working nights and weekends to build a social running app that feels up to par with today's standard for consumer mobile experiences.
Motivation + download link below:
We built a custom animatable, collision-aware, collapsible annotation system on Google Maps. Huge UX improvement but we lost tilt support along the way.
We finally cracked the math and extended our projection calculations adding a whole new dimension to the map. Just gorgeous.
Can you doomscroll an LLM?
I wanted to imagine what an AI native Q&A site would look like
It uses your previous conversations to generate new questions & answers from personas of your favourite thinkers: