aifaq.wtf

This is very much related to Generative Agents: Interactive Simulacra of Human Behavior, where 25 GPT-simulated characters hung out in a simulated town.

“Generative agents wake up, cook breakfast, and head to work,” the researchers wrote in a preprint paper posted to the arXiv outlining the project. “Artists paint, while authors write; they form opinions, and notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day.”

The interesting part of the paper (IMO) is less NPC's planning parties and more the reflective process they use to create memories to carry forward. It's basically REM sleep.

I feel like I waited years to understand the difference between how each type of document chain affected the output. And here we are!

Manager uses ChatGPT to generate the job posting, you use Langchain to apply for the job, HR's AI filters you out based on keywords, then the government's automated system rejects your welfare benefits.

"Write me a summary" seems like an easy task for a language model, but there are a hundred and one ways to do this, each with their own strengths and weaknesses. Even within langchain!

If you're excited about summarization, be sure to read this to see how things might go wrong. With hallucinations, token limits, and other technical challenges, LLM-based summarization has a lot more gotchas than you'd think.