I wanted to have AI generated characters for my virtual world for YEARS!
It wasn't really production ready until gpt-image-2
This is a virtual world that I have for my online school. It's like a video game where kids can connect with each other. I'm sure they'll love this.
I’m taking this course at Stanford where the final project is to build a one-person frontier lab.
Every Tuesday and Thursday there’s a guest speaker that shares their story and it’s been amazing to learn from them.
My project is frontier ai for education
@bilbeny I’ve also been thinking about this since the clawcon. Seems to me like the agent runtime (openclaw, cc) is the OS layer from the PC revolution in the 80s and the skills + tools are the application software layer.
@yoheinakajima@falkordb I was just thinking about that last week. For many use cases it makes more sense to have memory in graphs. I’ll take a look at falkor
“Even the best models will hallucinate, there are some tasks AI will never replace”
When you hire an employee you expect they will mess up once in a while. We should think the same of AI.
@adriamatz I switched because I needed more complex queries but miss how fast it was to go from idea to launch with firebase.
I’m now trying convex for a new project, apparently is the cool new db
Tried replacing claude code with @opencode + glm-4.7 this weekend because people said it was on par with opus 4.5 at only $30/year
I fell for it and subscribed to Z AI, claiming to give 3x more usage compared to Claude pro, but there’s a catch…
Gather town doubled their price so I thought I could build my own.
I just learned to deploy my own WebRTC server on hetzner in a couple of hours.
Turns out it’s super easy!