propertiesWhat
Artificial Intelligence
Testing language models (and prompts) like we test software The duty: an LLM email-assistant How you can test: properties What to check The testing process: an example Conclusion
TL;DR: it's best toChatGPT provided a hypothesis for what ties those emails together. Whether that hypothesis is correct or improper, we will see how the model does on the brand new examples it generates....
Recent posts
