LLM self-play on 20 Questionsgpt-3.5-turbo has a score of 68/1823 playing 20 questions with itselfMar 27, 20231Mar 27, 20231
Probing Compositional Understanding of ChatGPT with SVGI ask ChatGPT to draw and explain programmatic SVG imagesDec 28, 20221Dec 28, 20221
The Language of Modificationsa short study on the languages of descriptions and modificationsDec 5, 2022Dec 5, 2022