Anthropic announces new test features like prompt generation, test suite generation, evaluation and batch testing in their Console.
This is an interesting development for LLM tracing, testing, and evaluation products like HumanLoop, LangSmith, BrainTrust, Parea, Freeplay etc. who I expect were hoping that the foundation model API providers wouldn't venture into these areas.
This is an interesting development for LLM tracing, testing, and evaluation products like HumanLoop, LangSmith, BrainTrust, Parea, Freeplay etc. who I expect were hoping that the foundation model API providers wouldn't venture into these areas.