Anything To JSON
AI
structured extraction model
SHOW HN2024
18points
8comments
#1,990of 3,515 in 2024
Top 57%of 2024 by points
How HN took it
QuietFewer than 5 comments about the project
2 positive, 1 neutral or asking, 0 mixed, 1 critical, out of 4 comments about the project.
Idea: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Chaining a small model for JSON structure saves the big model's attention for reasoning
From 1 comment
Nice, makes sense to chain models so you don't waste the attention of the big smart model on the grunt work of JSON structure. I bet there are some good post-processing…
yeldarb on HN
Objections
Small model cannot match large closed-source models
From 1 comment
How does it differentiate from using json output with OpenAI? I think it can be useful for some cases, but you’ll always have the limitation of the model size to compete against…
Oras on HN
Hallucinates values for missing fields, such as inventing a name
From 1 comment
interesting idea! yeah next big challenge for us is hallucination in null fields (IE: if you ask for a "name" from text that doesn't have a name you usually get "John") so need…
edunteman on HN
Requests
Support for image inputs
From 1 comment
Awesome, agree on the nulls! Any plans to add support for image inputs?
1997 on HN
Questions
How it differs from OpenAI JSON mode
From 1 comment
How does it differentiate from using json output with OpenAI? I think it can be useful for some cases, but you’ll always have the limitation of the model size to compete against…
Oras on HN
Alternatives named
OpenAI JSON mode
From 1 comment
How does it differentiate from using json output with OpenAI? I think it can be useful for some cases, but you’ll always have the limitation of the model size to compete against…
Oras on HN