News for hackers. Stuff that matters.

A comment on Show HN: An authority gate for AI-generated customer communication. Parent comment

Re:Show HN: An authority gate for AI-generated customer comm... by chrisjj on Friday December 26, 2025 @03:50PM (#46396091)
I don't see that scale of drafting makes any difference. Reliability is entirely down to the training.

Also I think confining irreversible outcomes to the results of commitments is unsafe. Consider the irreversible outcome of advice that leads to customer quitting. There isn't a separate "layer" here.

[ Parent | on HN ]
Re:Show HN: An authority gate for AI-generated customer comm... by bhaviav100 on Friday December 26, 2025 @04:55PM (#46396739)
These are two different control problems.

Training governs what a model tends to say. Authority governs what is allowed to be acted on.

You can’t pre-block bad advice, but you can pre-block unapproved financial or contractual actions.

That’s the scope.

[ Parent | on HN ]
Re:Show HN: An authority gate for AI-generated customer comm... by chrisjj on Saturday December 27, 2025 @04:40AM (#46400516)
They are the same problem, since the actions are saying.

"AI-generated messages making commitments no one explicitly approved. Refunds implied. Discounts promised. Renewals renegotiated."

And if you can't block bad advice, you have a bigger problem since you cannot block resultant contractual action by the recipient e.g. termination.

[ Parent | on HN ]