Nathan Bos, Ph.D.inTowards Data ScienceLanguage Models and Spatial Reasoning: What’s Good, What Is Still Terrible, and What Is ImprovingA review of capabilities as of July 20243d ago23d ago2
Nathan Bos, Ph.D.Do I have to be polite to my LLM?It won’t change results much, but it might be good for youMar 31Mar 31
Nathan Bos, Ph.D.What your GPT RAG can’t seeBlind spots give insight into the mind of an LLMJan 15Jan 15
Nathan Bos, Ph.D.Will a language model tell me when I’m being lied to?You’ve recently taken in a teenaged relative. She’s failing in school and says she needs a better study environment. You seek helpful…Nov 1, 2023Nov 1, 2023
Nathan Bos, Ph.D.Language models can explain comedy but can’t write itCould AI write a good scene for Community or The Office?Aug 30, 2023Aug 30, 2023
Nathan Bos, Ph.D.Can a language models understand human taste?Probing GPT and Bard’s judgment about food flavors, textures and preparation. Special bonus recipe for chicken-fried lemon sorbet.May 29, 2023May 29, 2023
Nathan Bos, Ph.D.What does GPT really think about humans?GPT filled out Big-5 personality tests for some people I made up. The results surprised me. It makes some inferences that I didn’t think it…May 16, 20231May 16, 20231
Nathan Bos, Ph.D.GPT-4 may have general intelligence, but don’t let it near your Easter eggs.Wherein I test GPT-4’s stacking abilities, find some flaws, and some weird misconceptions.Apr 9, 20231Apr 9, 20231
Nathan Bos, Ph.D.Prompting better ‘Theory of Mind’ performance from Large Language modelsAnd, trying to help GPT-3 from being so gullibleMar 28, 20231Mar 28, 20231