Automorphic
AI
structured output from llms
SHOW HN2023
How HN took it
2 positive, 11 neutral or asking, 1 mixed, 4 critical, out of 18 comments about the project. Thread score -0.14.
Idea: 2 for, 2 againstDocs: 0 for, 1 againstExecution: 0 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
Constrained token generation approach is a sound technique
From 1 comment
the more it goes, the more I realize that the true power of LLMs is not in unstructured text that they can generate, but in structured output. but there are two approaches to…
behnamoh on HN
Objections
Playground model got a simple height conversion wrong
From 1 comment
oh its 100% predictable alright, predictable to be garbage : the default example chooses height as the wrong "number" whatever that might assume to be, then if you try to change…
beefnugs on HN
Self-hosting framing was misleading; primarily a SaaS
From 1 comment
I think the references to this being a “tool” that you can “self-host if you want” are a little disingenuous, especially after seeing that the linked GitHub project doesn’t…
foundry27 on HN
Token savings argument is weak for small JSON outputs
From 1 comment
Point 1 doesn't feel like a good enough reason. The number of tokens outputted as a JSON is so small if you tell GPT to output it properly.
jacky2wong on HN
Requests
Explain differences from guidance and OpenAI functions
From 2 comments
What are the benefits over https://github.com/microsoft/guidance/ ?
sunshadow on HNCould you contextualise this against OpenAI’s native functions?
darkteflon on HN
Questions
Is the model available on HuggingFace
From 1 comment
You mention self hosting the model. Do you have the model weights up on HuggingFace?
easygenes on HN
Alternatives named
Guidance (Microsoft)
From 2 comments
What are the benefits over https://github.com/microsoft/guidance/ ?
sunshadow on HNguidance is a dead project. it worked well as a hobby side project by MS researchers, but it clearly isn't a long-term solution as new LLMs are introduced.
behnamoh on HN
LMQL
From 1 comment
What about LMQL?
amkkma on HN
OpenAI function calling
From 1 comment
Can easily be done with OAI's new function calling.
marban on HN
parserllm
From 1 comment
What's the difference between self hosting this and manually running https://github.com/r2d4/parserllm ?
Janymos on HN