Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
koakuma-chan
4 days ago
|
parent
|
context
|
favorite
| on:
LLM Structured Outputs Handbook
Is there evidence that LLMs adhere to this format better than to JSON? I doubt that.
iLoveOncall
4 days ago
|
next
[–]
It is 100% guaranteed that they DON'T. Toon is 3 months old, it's not used by anyone, and it's therefore not in the training set of any model.
reply
TheTaytay
4 days ago
|
prev
[–]
Their benchmarks compare it against other formats as input, not as output.
reply
koakuma-chan
4 days ago
|
parent
[–]
Now it makes sense.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
