Hacker News new | ask | show | jobs
by jkcorrea 365 days ago
if scaling laws and context windows continue, why not?
1 comments

There is coming a very_soon_time whereby one will have to ensure all the routes and failure_modes for the AIs plumbing are functional.

What if the outage is specifically that AI_agent cant reach [thing]?

> What if the outage is specifically that AI_agent cant reach [thing]?

We already saw some examples of this in Anthropic's safety papers - the AI will reach out to the human to get help with that - essentially using a human as an API/tool.

Or it will contact the FBI