This post fully captures why I 💙 MCP servers so much (as noted, it has nothing to do with "AI").
https://worksonmymachine.substack.com/p/mcp-an-accidentally-universal-plugin
This post fully captures why I 💙 MCP servers so much (as noted, it has nothing to do with "AI").
https://worksonmymachine.substack.com/p/mcp-an-accidentally-universal-plugin
Sigh. I'm still so bothered by that "chatgpt rots your brain" paper BECAUSE it correctly positions some of the compelling questions we have about LLM usage but then does us all a disservice in its approach, pushy interpretation, and inappropriate or misleading framing of brain evidence and measurement of human problem-solving, imo
I am asking myself: what studies would *I* design to evaluate people's usage of LLMs in keeping with learning science and without neurohype?
Watching Microsoft’s robots telling Microsoft’s other robots that they need to agree to Microsoft CLAs in between Microsoft’s developers begging Microsoft’s robots to actually understand the problems they’re trying to fix in Microsoft's platform code on Microsoft's version-control website is kind of amazing.
This is definitely the future Terry Gilliam promised us.