Microsoft* put together a prompt library for GPT-4 for educators, students, & admin using some of our prompts as a basis. Add your own!

*We do not take any compensation from them or any other AI company pic.twitter.com/SA8oeO4Pho

Test the ability of AI to do the work (over 90% on exams, the field is “on the verge of a paradigm shift”)

And suggest how to change training as a result. arxiv.org/pdf/2307.02792… pic.twitter.com/wcZNBx4mMF

Challenges at the interface of medical statistics and AI are population inference vs. prediction, generalizability, reproducibility and interpretation of evidence, and stability and statistical guarantees. nej.md/48umvVq pic.twitter.com/VHR1ioM5JQ

> you Google
> Quora spots query and id’s as frequent
> Quora uses ChatGPT to generate answer
> ChatGPT hallucinates
> Google picks up Quora answer as highest probability correct answer
> ChatGPT hallucination is now canonical Google answer pic.twitter.com/qInLfIMGtc

The new revision is mostly small corrections, but also updates to how we display the logic of the prompts we use. papers.ssrn.com/sol3/papers.cf… pic.twitter.com/J5E4msxHXA

Develops a method to enable LLMs to “deliberate” on responses to correct mistakes.

Steps:
1) draft initial response
2) plan verification questions to fact-check the draft
3) answer questions independently to avoid bias from… twitter.com/i/web/status/1… pic.twitter.com/IuC4uVGKAA