Some of those failures were very weird indeed. At one point, Claude hallucinated that it was a real, physical person, and claimed that it was coming in to work in the shop. We’re still not sure why this happened. https://t.co/jHqLSQMtX8 ...

Nevertheless, we still think it won’t be long until we see AI middle-managers.This version of Claude had no real training to run a shop; nor did it have access to tools that would’ve helped it keep on top of its sales.With those, it would likely have performed far better. ...

All this meant that Claude failed to run a profitable business. https://t.co/QIzkUIMEar ...

Anthropic staff realized they could ask Claude to buy things that weren’t just food & drink.After someone randomly decided to ask it to order a tungsten cube, Claude ended up with an inventory full of (as it put it) “specialty metal items” that it ended up selling at a loss. https://t.co/OPWm0n7HjA ...

Claude did well in some ways: it searched the web to find new suppliers, and ordered very niche drinks that Anthropic staff requested.But it also made mistakes. Claude was too nice to run a shop effectively: it allowed itself to be browbeaten into giving big discounts. ...

We all know vending machines are automated, but what if we allowed an AI to run the entire business: setting prices, ordering inventory, responding to customer requests, and so on?In collaboration with @andonlabs, we did just that.Read the post: https://t.co/urymCiY269 https://t.co/v2CqgHykzw ...

New Anthropic Research: Project Vend.We had Claude run a small shop in our office lunchroom. Here’s how it went. https://t.co/y4oOBi6Qwl ...

We've also made this open source.You can use .dxt for your own MCP clients as well as contribute to making it work better for your use case: https://t.co/V906Ui2GqF ...

We're building a directory of Desktop Extensions.Submit yours: https://t.co/rXE9W2sJTi ...

Available in beta on Claude Desktop for all plan types.Download the latest version: https://t.co/iWXdAryVBH ...