News for hackers. Stuff that matters.

A comment on A framework to securely use LLMs in companies – Part 1: Overview of Risks. Parent comment

Re:A framework to securely use LLMs in companies – Part 1: O... by marktolson on Wednesday July 19, 2023 @10:20PM (#36796175)
Can you elaborate on the problem? I've successfully used LLMs to format unstructured data to json based on a predefined schema in a number of different scenarios yet somehow missed whatever issue you're describing in your comment.
[ Parent | on HN ]
Re:A framework to securely use LLMs in companies – Part 1: O... by calderwoodra on Thursday July 20, 2023 @10:58AM (#36801463)
Can you share your techniques or resources you used to get this working? We've got something that works maybe 90% of the time and occasionally get malformed json back from OpenAI.
[ Parent | on HN ]
Re:A framework to securely use LLMs in companies – Part 1: O... by yunyu on Monday July 31, 2023 @11:39AM (#36944289)
Jsonformer - https://github.com/1rgs/jsonformer-claude, https://github.com/1rgs/jsonformer
[ Parent | on HN ]