Seven days ago, we started an experiment in Recursive Self-Improvement (RSI).
We wanted to explore a simple question: What happens when we let an AI agent iteratively improve its own harness?
So we let Lobe Agent run for an entire week, using our RSI framework to explore and
Ian Silber's website has everyone debating whether a résumé like this would actually get you hired.
Meanwhile, we made a LobeHub version and put our own "résumé" on it 🏒
Now we're curious. Would this make you want to know more about LobeHub?
Gemini 4 Carbon just landed on LobeHub! 🚀
So we decided to have a little fun with it.
Gave Carbon and Opus 5.5 the exact same prompt: make a rainbow jelly you can poke, squish, and play with. 🌈
Same prompt. Two very different results.
Which jelly would you pick? 🍮
Claude Fable 5.2 is now on LobeHub! 🎉
We tried something fun with this one.
Gave Fable 5.2 and Opus 5.5 the exact same prompt and asked them to build a 3D scene.
Here's how it went:
Fable 5.2: ~10 min, $1.20
Opus 5.5: ~5 min, $0.70
Opus finished in half the time and cost