Elektrine lite

← Feed

@trenner@mastodon.social

2026-08-24 10:32 UTC

@bearbob@hachyderm.io @norootcause@hachyderm.io @saraislet@infosec.exchange Agreed. A core skill when coding with LLMs is knowing when to step in to tell the LLM to stop - they almost never find that limit correctly themselves. I have no idea why that would be any different for on-call automation. The technology has very limited ability to assess confidence in an approach by itself.

Replies (0)

No replies.