Generative AI workflows and hacks 2023

March 23, 2023 — April 26, 2023

I will try to attempt synthesis of LLM hacks elsewhere. This where I keep ephemeral notes and links.

1 Prompt engineering

1.1 Writing matters

1.2 Coding matters

2 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

3 Information search matters

4 Left-field

5 Edge LLMs

Figure 1

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

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

6 Incoming

7 References

Kim, Baldi, and McAleer. 2023. Language Models Can Solve Computer Tasks.”
Suzgun, Scales, Schärli, et al. 2022. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.”
Wang, Wei, Schuurmans, et al. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models.”