DeepSeek-R1 System Prompt: Leak or Hallucination?From the “here is why testing generative AI is hard” dept: Here is the actual response output from an utterance I gave DeepSeek-R1 (minus…Jan 29Jan 29
Testing LLMsThere are a number of roles in an org that may need to validate output from an application:Nov 10, 2023Nov 10, 2023
Some Thoughts On AI Training Data and the PublicI recently ran across an article on Bruce Schneier’s blog proposing the idea of an “AI Dividend” similar to Alaska’s Permanent Fund, which…Jul 11, 2023Jul 11, 2023
chatGPT Models ExperimentI’ve been playing with chatGPT lately, and recently started experimenting with it through the OpenAI API using python. Since I’m relatively…Feb 23, 2023Feb 23, 2023