Lets gooo first of many from last week! Lmk how you end up playing w this 🔥

💻 We've got some CODE EXAMPLES to help you get started with the #UnstructuredMCP Hackathon! Check out this compact MCP server example that processes unstructured documents for Claude Desktop: bit.ly/4j5EJRz And our official (actively developed) MCP server

Ahmad Al-Dahle You really need a better cannonical chatbot than meta.ai - it's just not good enough to show off what the best models optimised for performance at scale are capable of. Do like Qwen and get Open WebUI to let people choose models and do real work.

More otw!!!

25yo me w new LLMs and their increasing performance

We observed o3 in particular has a propensity to try to “hack” our tasks to get a higher score. Importantly, we saw this arise naturally from the model without explicit nudging. Behaviors like these have required us to be more careful in how we evaluate model capabilities.

Damn

Built this with MCP, Unstructured and Databricks to start off DocProc workflows with plaintext! Go through the setup instructions, provide Claude what it needs and you get workflows up and running in minutes🙂

🛠️ Want to build a complete ETL pipeline for your unstructured data? Join us next Tuesday 4/29 for a hands-on walkthrough of Unstructured's Workflow Endpoint and API. Maria Khalusova will be showing you how to: 🔹 Connect to S3 as your source 🔹 Preprocess with partitioning,

LangGraph has been one of the easiest/most customizable tools I've used recently to build Agentic Workflows. Every workflow is a graph, each node is a function call. Make a couple nodes LLMs and you have an Agentic workflow all set up.

Reimplementing backpropagation from scratch has been humbling. Crazy how much we take autograd for granted

So, a brain?