Re:Talk Is Cheap: The Operational Impact of LLM Use
by ozlikethewizard on Sunday May 31, 2026 @01:24PM
(#48347560)
This is discussed in the article, and I think the author makes pretty reasonable arguments for why by nature we will not see the reliability of LLM usage improve. They also discuss what I agree as the more effective method of using an LLM is, as a feedback and refinement tool, not a decision maker.
[ Parent
| on HN ]
Re:Talk Is Cheap: The Operational Impact of LLM Use
by gtirloni on Sunday May 31, 2026 @05:19PM
(#48349867)
> This is not a limitation that can be overcome by LLMs. Their generative value is in their unreliability. If you turn temperature down to zero, you get a deterministic machine - but you also break every meaningful application I know of in production.
This is not a reasonable argument. Setting the temperature down to zero does NOT give you a deterministic machine. And I have never seen that break any application in production, quite the contrary.
Re:Talk Is Cheap: The Operational Impact of LLM Use
by oudlys on Tuesday June 09, 2026 @08:19AM
(#48460135)
By “break” I don’t mean “won’t function”. I mean “won’t deliver on their value proposition”. A functioning product is a necessary, but not a sufficient condition for technology to have utility. I would defend vigorously that the generative value in LLMs is derived from their unreliability. Which is what the argument ultimately rests on.