alt Hacker News>and then pulls the slot machine lever over and over
Does anyone really do this? You want verification and self-correction in a loop, not rerolling and cherrypicking. The non-determinism point is really tiresome to hear over and over.
Replies
MattDamonSpace • today at 1:39 AM
The slot machine metaphor gets thrown around a lot but it hasn’t really described my experience with LLMs since ~2024
girvo • today at 1:37 AM
> Does anyone really do this
Yes, lots of people. It’s a whole issue.
bigstrat2003 • today at 2:16 AM
> The non-determinism point is really tiresome to hear over and over.
When the problem is fixed, you'll stop hearing about it.
➕ show 1 reply
I do this for debugging. Models are extremely vulnerable to framing effects and it's usually easier to spin up a fresh instance than it is to get an existing one to generate new hypotheses.