[sgk284]

Fun post! Back during the holidays we wrote one where we abused temperature AND structured output to approximate a random selection: https://bits.logic.inc/p/all-i-want-for-christmas-is-a-rando...

[onionisafruit]

I enjoyed that.

When you asked it to choose by picking a random number between 1 and 4, it skewed the results heavily to 2 and 3. It could have interpreted your instructions to mean literally between 1 and 4 (not inclusive).

[sgk284]

Yea, absolutely. That's a good point. We could have phrased that more clearly.

[LourensT]

could you use structured output to make a more efficient estimator for the logits based?

[sgk284]

The two mechanisms are a bit disjoint, so I don't think it's the right tool to do so. Though it could have been an interesting experiment.