Marek Sivak retweeted
I've been frustrated with the linear chat experience for learning, so I used Fable to help rethink it.
Introducing Rabbithole 🐇, an infinite canvas where you can select anything, ask anything, and your questions branch instead of stack.
This lets you pull on a thread until your curiosity is satisfied, then easily step right back to where you started.
Completely changed the way I learn with AI.
Marek Sivak retweeted
Replying to @elwatto
I don’t write them anymore. I am now running inception essentially. I ask the agent to write a prompt that contains a goal and a loop that will achieve this goal.
Usually one sentence. I let it optimize it and then run it. Works like a charm.
Marek Sivak retweeted
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
Amazing project and I love the design too
Also great doman name 👌
howmuch.tax
Marek Sivak retweeted
This demo is built with React Native (Skia + Reanimated) and is open source: reactiive.io/demos
Marek Sivak retweeted
What do these smell like?
One-shotted in @variantui, if you'd like to try we're bringing on a few more beta testers
Marek Sivak retweeted
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:
Marek Sivak retweeted
This app idea has huge potential:
A day planner that helps you visualize your day
Marek Sivak retweeted
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.






































