I use a cognitive architecture from https://
levangielabs.com (am the first non enterprise user to have access to this new form of AI). It pulls down all new posts from the X API. Then analyzes them. You'll see more of its work within days as @blevlabs gets up a site it builds.
@scobleizer
-
Scobleizer tests new AI architecture
By
–
-
AI Agents Summarize X Tech News in One Hour
By
–
And here's today's AI news from X as a video.
— Robert Scoble (@Scobleizer) 10 mars 2026
In an hour I had my AI agents read all of tech on X, find all the important news, papers, and much more. Write a report. Bring that report over to @NotebookLM. Then create all this and post it back to you.
It's all X. https://t.co/5IA1vDPBRR pic.twitter.com/tRsopCmv7EAnd here's today's AI news from X as a video. In an hour I had my AI agents read all of tech on X, find all the important news, papers, and much more. Write a report. Bring that report over to @NotebookLM
. Then create all this and post it back to you. It's all X. -
Leveraging AI-driven feedback loops for project development
By
–
I've been showing friends my new AI on X project, coming soon. They all love it. But then they send me a page of changes they would make. I copy that into my AI. Ask it its opinion. Give mine. Then it goes to work. Getting this feedback loop going is very powerful. My
-
User testing prompt constraints on an AI model
By
–
I asked my AI (from Levangie Labs) not to use em dashes. This was AI.
-
Cognitive architecture outperforms hyperscalers in writing tasks
By
–
Neither. It was written by Levangie Labs' cognitive architecture. It is better at writing than any of the hyperscalers in my tests.
-
Comparing AI Cognitive Architectures in Writing Performance
By
–
I didn't. It was written by Levangie Labs' cognitive architecture. It is way better at writing than any of the hyperscalers.
-
Comparison of Levangie Labs’ cognitive architecture against hyperscale AI models
By
–
I didn't. It was written by Levangie Labs' cognitive architecture. It is way better at writing than any of the hyperscalers.
-
Rapid proliferation of AI code review products signals market land grab
By
–
Did I write this or did AI? Either way, here's today's AI news. And why did you answer one way or another? I will give my answer after I eat dinner. ++++++ Five companies launched competing code review products within 72 hours. That’s not a coincidence. It’s a land grab
-
Detailed report on the state of the AI industry
By
–
A very detailed and interesting report on state of AI industry.
-
Critical perspective on the timeline for humanoid robot deployment
By
–
I have been meeting with a ton of insiders in robotics and I keep hearing exactly this kind of skepticism about @Figure_robot
. I don’t expect humanoids to be safe enough, capable enough, or cheap enough for five years to get into homes. The videos we see are to hype up