[atleastoptimal]

Weird that a company releases an article about how it can barely control the output of its own model

[jafitc]

Sounds like you have a lot of firsthand experience with their model. Also like you "barely" read the article.

[atleastoptimal]

lots of Anthropic shilling from this account

[jafitc]

I have a GPT-4 subscription, but not for Claude because GPT-4 is a better overall model. Still used both extensively. Claude just works better for insight extraction from long context. To say that it's "barely" doing what it's supposed to be doing smells like no experience with the actual model to me. So I call it out.