Re:Show HN: LLMs can generate valid JSON 100% of the time
by padjo on Monday August 14, 2023 @05:29PM
(#37127056)
It’s starting to feel like LLMs are to “classical” software engineering what quantum physics was to classical physics
Re:Show HN: LLMs can generate valid JSON 100% of the time
by catlifeonmars on Monday August 14, 2023 @08:55PM
(#37128809)
How so? I’m not quite following the analogy.
Re:Show HN: LLMs can generate valid JSON 100% of the time
by antonvs on Monday August 14, 2023 @10:00PM
(#37129265)
Just guessing what was meant, but quantum physics in some sense tries all possible paths before an outcome is selected.
The problem with that is that without a quantum computer, or without some sort of filtering, that process can take up to infinite time.
Re:Show HN: LLMs can generate valid JSON 100% of the time
by padjo on Tuesday August 15, 2023 @06:50AM
(#37132328)
Oh it was just a glib way of moaning about non-determinism making its way into software engineering. Much like how physicists had to make peace with the probabilistic nature of quantum physics.
Re:Show HN: LLMs can generate valid JSON 100% of the time
by kristjansson on Tuesday August 15, 2023 @01:49AM
(#37130648)
Why wait for OpenAI?
right now you can inject prompts that the LLM takes into consideration before the output
I wonder if you can make it have a "post" generation function that says like "keep re-trying in a loop (aka hallucinating with randomness) until the output message passes XYZ format/checks/scoring"