[lightweb]

LLMs still leave something to be desired for DevOps related work; infrastructure code. There is still not really enough context available when crossing the division between the hardware, OS, and software.

For Terraform, specifically, Claude 4 can get thrown into infinite recursive loops trying to solve certain issues within the bounds of the language. Claude still tries to add completely invalid procedures into things like templates.

It does seem to work a bit better for standard application programming tasks.

[bpt3]

It's not surprising to me that it struggles with a language where there aren't billions of lines of code available to use as training data.

I wonder if that's all it is, or if the lack of context you mention is a more fundamental issue.