Yennie Jun

A mini multi-agent competition among 3 different LLM agents Yennie Jun · Follow Published in Towards Data Science · 6 min read · 12 hours ago — Generated using ChatGPT 4o. This article was originally posted on Art Fish Intelligence. Introduction LLMs are good at many things, and one of those things is playing games. People have used LLMs to play all sorts of games such as Minecraft, Chess, murder mystery games, Werewolf, and the

There is a race towards language models with longer context windows. But how good are they, and how can we know? Yennie Jun · Follow Published in Towards Data Science · 9 min read · 9 hours ago — The context window of language models have been growing at an exponential rate in the last few years. Figure created by the author. This article was originally published on Art Fish Intelligence. Introduction The context window

How do language models handle conflicting instructions in its prompt? Yennie Jun · Follow Published in Towards Data Science · 7 min read · 6 hours ago — Given contradictory instructions in the system message, the prompt, and examples, which instructions will an LLM follow in its response? Created by the author. How do language models handle conflicting instructions in a prompt? Cognitive dissonance is a psychological term describing the mental discomfort experienced by an