Demolishing the “We’re hitting a brick wall because we’re running out of human training data” theory - LARGE LANGUAGE MODELS CAN SELF-IMPROVE, Oct 2022
“We show that it is possible for the LLM to self-improve even on its own generated questions and few-shot Chain-of-Thought prompts.”
(Numerous subsequent papers further strongly confirming this.)
Paper
“We show that it is possible for the LLM to self-improve even on its own generated questions and few-shot Chain-of-Thought prompts.”
(Numerous subsequent papers further strongly confirming this.)
Paper
👍12🤬2❤1💯1
Using GPT4 to Make an AI Bartender App
“Last time I made an app it took almost 6 months and nearly $10K in art costs. This time we built the app in about a week and then took a couple of weeks to test and refine it. We used GPT4 to help build the app, which is based on the OpenAI’s GPT API. We also used AI tools for all of the graphics, from the icon to the bartender animations, bar backgrounds, and voices. In this post we’ll touch on the tools used to create the app. The cost of creating the app has been super-low.”
Article
“Last time I made an app it took almost 6 months and nearly $10K in art costs. This time we built the app in about a week and then took a couple of weeks to test and refine it. We used GPT4 to help build the app, which is based on the OpenAI’s GPT API. We also used AI tools for all of the graphics, from the icon to the bartender animations, bar backgrounds, and voices. In this post we’ll touch on the tools used to create the app. The cost of creating the app has been super-low.”
Article
👍24❤4👨💻2
retroactively applying generational labels backward through time
Founding Fathers are Generation L&M
Founding Fathers are Generation L&M
❤8👍2