Pydantic schema prompts fail differently across nine LLM setups
Of 3,997 attempts, fenced JSON was the top failure, and only 48.0% of 681 fenced cases passed after fence removal.
1 stories, newest first · one card per story
Of 3,997 attempts, fenced JSON was the top failure, and only 48.0% of 681 fenced cases passed after fence removal.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views