SD XL has been suffering from CLIP – I think this is true, at least partially. Recent models have shown some potential related to natural language, like understanding "left is red, right is blue". However, since CLIP was not trained with natural language sentences, base SD XL and its finetuned variants were significantly limited regarding processing it.

Model Context Protocol (MCP) has stirred up quite a storm on Twitter—but is it actually useful, or just noise? In this debate, Harrison Chase (LangChain CEO) and Nuno Campos (Head of LangGraph) discuss whether MCP lives up to the hype.

Harrison's Take: MCP Is Actually Useful

I started skeptical about MCP, but I've begun to see its value. Essentially: MCP is useful when you want to add tools to an agent you don't control.