greglee
Ask HN: How are you testing your LLM applications?
I'm looking to test an LLM application that uses a combo of LLM calls, Tool calls, code, and RAG. Testing will be both in production (errors, regressions) and in development (isolate a part of the system, iterate, run experiments). Would you use a platform or roll your own solution?LangSmith looks interesting with tracing+playground, but I'm not using LangChain. I'm seeing established companies...
Re:
on Thursday April 13, 2023 @03:30PM (#35560913)
The building blocks of general AI, inspired by biology.
Re:Show HN: Subscribe to AI-Generated summaries of top new AI articles
on Thursday April 06, 2023 @03:43PM (#35473376)
We felt the pain of keeping up with the 100+ AI papers published daily on Arxiv. So, we built this newsletter to provide AI generated summaries of those papers every day, using the BART. This version is super bare-bones. Let us know if you find this useful, and we will continue to improve it!