6/ "GPT is all you need for the backend" https://
github.com/TheAppleTucker
/backend-GPT
…
Tired: use an LLM to help you write a backend
Wired: LLM is the backend
Inspiring project from a recent Scale hackathon. The LLM backend takes state as JSON blob and modifies it based on… English description.
@karpathy
-
GPT as Backend: LLM-Powered State Management with Natural Language
By
–
-
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. -
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. -
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. -
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 -
Move Test Time Compute to Training Time When Possible
By
–
it's good except as a rule of thumb you always want to move test time compute into train time compute, to whatever extent possible.
-
Content-Conditioned Q&A Assistants: A Future Feature
By
–
content-conditioned Q&A assistant is a prominent feature of the future.
-
Step-by-Step Thinking Needs Correct Answers in GPT Models
By
–
One of my favorite results in 2022 was that it's not enough to just think step by step. You must also make sure to get the right answer 😀 https://
sites.google.com/view/automatic
-prompt-engineer
…
(actually a nice insight into a psychology of a GPT; it pays to condition on a high reward)