8/ These examples illustrate how prompts 1: matter and 2: are not trivial, and why today it makes sense to be a "prompt engineer" (e.g. @goodside ). I also like to think of this role as a kind of LLM psychologist.
LLMS
-
ChatGPT iOS Shortcut Creates Advanced HomeKit Voice Assistant
By
–
5/ "ChatGPT in an iOS Shortcut — Worlds Smartest HomeKit Voice Assistant" https://
matemarschalko.medium.com/chatgpt-in-an-
ios-shortcut-worlds-smartest-homekit-voice-assistant-9a33b780007a
… This voice assistant is significantly more capable and personalized than your regular Siri/Alexa/etc., and it was programmed in English. -
Prompts Enable Complex Multi-Step Reasoning Through Strategic Design
By
–
2/ These two [1] https://
arxiv.org/abs/2205.11916 , [2] https://
arxiv.org/abs/2211.01910 are good examples that the prompt can further program the "solution strategy", and with a good enough design of it, a lot more complex multi-step reasoning tasks become possible. -
Prompting GPTs: Ask for the performance you want
By
–
3/ These two articles/papers: [1] https://
evjang.com/2021/10/23/gen
eralization.html
… [2] https://
arxiv.org/abs/2106.01345 bit more technical but TLDR good prompts include the desired/aspiring performance. GPTs don't "want" to succeed. They want to imitate. You want to succeed, and you have to ask for it. -
Building a Virtual Machine Inside ChatGPT with English Programming
By
–
4/ Building A Virtual Machine inside ChatGPT https://
engraved.blog/building-a-vir
tual-machine-inside/
…
Here we start getting into specifics of "programming" in English. Take a look at the rules and input/output specifications declared in English, conditioning the GPT into a particular kind of role. Read in full. -
LLMs In-Context Learning and Prompt Programming Capabilities
By
–
This tweet went wide, thought I'd post some of the recent supporting articles that inspired it.
1/ GPT-3 paper showed that LLMs perform in-context learning, and can be "programmed" inside the prompt with input:output examples to perform diverse tasks https://
arxiv.org/abs/2005.14165 -
GPT-3 and GPT-3.5 Pass Theory of Mind Tests at Human Levels
By
–
This article isn't getting enough attention: GPT-3 is able to pass Theory of Mind Test at 7yr old human level, GPT-3.5 at a 9yr old level (They did not use questions that are in the training dataset.) What will GPT-4 be capable of? https://
arxiv.org/abs/2302.02083 -
AI21 Labs AMA Session with NLP Experts on Discord
By
–
Curious to learn more about our models? Join our upcoming AMA session this Wednesday, hosted by our NLP experts and Developer Advocates Yotam Shinan and Yuval Belfer. Head over to our Discord, "AMA #1," and get ready to ask us your burning questions https://
discord.com/invite/7YqhxMVS -
Word and Sentence Embeddings: Building Blocks of Large Language Models
By
–
Did you know that word and sentence embeddings are the building blocks of most large language models? Learn more about how they work and how they're used to understand human language in this exciting piece by luis_likes_math
-
Question to gwern on updated instructions and model retuning
By
–
@gwern Any new thoughts on this in light of the apparently updated instructions (against discussing “life, existence, or sentience,” arguing with the user, etc.)? Do you think the model was re-tuned, rather than given a prompt update?