Generative AI workflows and hacks

Prompt engineering
- Writing matters
- Coding matters
Economics of
Information search matters
Left-field
Edge LLMs
Incoming
References

Prompt engineering

Deeplearning.ai ChatGPT Prompt Engineering for Developers
Prompt Engineering Guide
Pinecone LangChain AI Handbook

Writing matters

Scientific Writing Is a Miserable Grind, So Let’s Outsource It to AI

Rattibha pro-tips: ChatGPT is everywhere and everyone is using it. But most academics don't know how to use it *smartly. part 1 part 2

Spoken speech is full of redundancies, repetitions, and false starts.
To clean it up, I needed to remove these redundancies
And that's where ChatGPT comes in.

Coding matters

openai/openai-cookbook: Examples and guides for using the OpenAI API
LMQL: Programming Large Language Models: “LMQL is a programming language for language model interaction.”
LMQL generalizes natural language prompting, making it more expressive while remaining accessible. For this, LMQL builds on top of Python, allowing users to express natural language prompts that also contain code. The resulting queries can be directly executed on language models like OpenAI's GPT models Fixed answer templates and intermediate instructions allow the user to steer the LLM's reasoning process.
This is how you code now
AI assisted learning: Learning Rust with ChatGPT, Copilot and Advent of Code
Using GPT-3 to explain how code works
A Datasette tutorial written by GPT-3
Mitchell Hashimoto on the mysterious ease of ChatGPT plugins

Economics of

This is the thing I am most deeply interested in theoretically

GPT and the Economics of Cognitively Costly Writing Tasks

To analyze the effect of GPT-4 on labor efficiency and the optimal mix of capital to labor for workers who are good at using GPT versus those who aren’t when it comes to performing cognitively costly tasks, we will consider the Goldin and Katz modified Cobb-Douglas production function

More at LLM economics

Information search matters

Left-field

Replacing an A/B Test with GPT — Count Bayesie

Edge LLMs

Running those big cloud models on the edge, i.e. locally.

Could you train a ChatGPT-beating model for $85,000 and run it in a browser?
Large language models are having their Stable Diffusion moment
Stanford Alpaca, and the acceleration of on-device large language model development
Transformers.js Run 🤗 Transformers in your browser!

Impressive example: mlc-ai/web-stable-diffusion: Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support..

Incoming

Open Brains

References

Kim, Geunwoo, Pierre Baldi, and Stephen McAleer. 2023. “Language Models Can Solve Computer Tasks.” arXiv.

Suzgun, Mirac, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, et al. 2022. “Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.” arXiv.

Wang, Xuezhi, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. “Self-Consistency Improves Chain of Thought Reasoning in Language Models.” arXiv.