Follow AI Builders — Not Influencers

This seems to have become the standard in Western Europe All last 3 hotels in Netherlands and Denmark didn't clean by default Voco in The Hague was especially wild, you had to put the regular room cleaning card outside but they said they will ignore that So they have another paper card you need to hang but even that wasn't enough to get them to clean our room We had to call every morning at 10am to explicitly ask for room cleaning Even then they wouldn't clean it until 3pm It seems there is either a staff shortage or just an unwillingness to pay for cleaning staff at all It boggles my mind, but I'm very hopeful robots will solve cleaning hotel rooms soon!

Our team is at CVPR 2026 if you want to come say hi :)

Hardest part about making educational content about AI is how frequently you have to remake videos. So many updates since I made these

RT LlamaIndex 🦙 Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or other unstructured documents. Contracts, invoices, reports... All have special layout, language, and context mixed together, and getting reliable structured data out of them is still one of the hardest unsolved problems in enterprise AI. Parse-Flow is an open-source project we built to tackle this head-on. It puts four document processing primitives at the center of a visual workflow designer: 📄 Parse — clean markdown and text from raw documents 🔍️ Classify — assign documents to user-defined categories ✂️ Split — segment documents into typed chunks 🪏 Extract — pull structured JSON against a schema You drag steps onto a canvas, drop in a document, and watch events stream back as the pipeline runs. Under the hood it's powered by a LlamaAgents workflow that walks your flow one step at a time, making every transition observable and every failure a first-class value. 📚️ Full write-up on the architecture here: https://www.llamaindex.ai/blog/designing-a-visual-document-intelligence-workflow-with-llamaparse?utm_medium=socials&utm_source=twitter&utm_campaign=2026-jun- 👩‍💻 Source code: http://github.com/run-llama/parse-flow

RT Josh Lehman OpenClaw is a big deal, but the systems that OpenClaw is pioneering to build software like this at agentic scale are at least as significant. This is where software engineering is going — pay attention.

The future of America is small businesses that can build faster than ever before with agents. Glad to support this with up to $25m in Computer credits ahead of America’s 250th anniversary 🇺🇸🇺🇸🇺🇸

wondering if @_catwu has an update on this chart post opus 4.8

RT Raphael Kalandadze This is the enterprise-agent security frame I like: treat agents like untrusted developers. They need the ability to call an API, not possession of the credential. Control plane outside runtime. Fail closed. Boring, but that is how this becomes deployable.