I suspect that, despite lacking specific training they are wide. pic.twitter.com/6ZQD9DFhRy

💡 LLMs have the potential to advance psychological measurement, experimentation and practice.

💡 LLM generated on-topic, grammatically correct useless information, but not based on research and psychology construct.

💡A critical… twitter.com/i/web/status/1… pic.twitter.com/Nt16kFnQ2r

But many folks have a hard time starting out on it.

Here’s how you can get started on Zotero in 15min:

Zotero for beginners: a step-by-step tutorial 🧵

There’s a massive library in Minecraft populated with uncensored articles, journals, and information from all over the world. It’s accessible worldwide and offers a unique opportunity to people in censored countries to view uncensored texts
pic.twitter.com/e7mypcdlMz

abs: arxiv.org/abs/2310.05910
code: github.com/IBM/SALMON

This paper from IBM proposes a new RLAIF paradigm that uses the LLM to judge responses based on specific principles, and trains a reward model conditional on… twitter.com/i/web/status/1… pic.twitter.com/9bGZMP1bz1

#JAMAai ⁦‪@Penn‬⁩

Watch on the JAMA Network YT: ja.ma/46gRGlg pic.twitter.com/2tEs230spb