Hacker News Reader

> There's also a worrying underlying assumption being made here that the answers your LLM will give you are accurate and trustworthy.

I first hand saw in, AWS devDays, an AI giving SIWINCH as "root-cause" of Apache error in a containerized process is in EKS for a backend FCGI process connection error. It has been extremely hard since that demo to trust any AI for system level debugging.

View on HN

If we were smart we'd use AI to grok a system in order to help us reduce its complexity. I don't think we're anywhere close to even being able to provide all the necessary context to solve problems like this.

(1) when was that? If it was less < 6months ago, the current gen of models is noticeably better

(2) AWS is not a leader, if even a contender, in the AI space. I would not evaluate the potential based on a demo they produced

Reply on news.ycombinator.com