Step 1: Train ChatGPT to be your coach – Visit ChatGPT (
http://
chat.openai.com)
– Copy/paste the prompt below (ALT text of the image)
– In this example, we will have one on one coaching from the great Steve Jobs
PROMPT ENGINEERING
-
Train ChatGPT to be your coach with Steve Jobs
By
–
-
Learning to Retrieve In-Context Examples for Large Language Models
By
–
Learning to Retrieve In-Context Examples for Large Language Models paper page: https://
huggingface.co/papers/2307.07
164
… Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the -
Mastering Unknown with GPT-4 Flipped Interaction Pattern
By
–
Mastering the Unknown with #GPT-4 and the Flipped Interaction Pattern
#AI #GenerativeAI @FrRonconi @labordeolivier @Nicochan33 @Shi4Tech @mvollmer1 @KanezaDiane @enilev @fogle_shane @Ym78200 @kalydeoo @enilev @Khulood_Almani @AkwyZ @amalmerzouk https://
towardsdatascience.com/mastering-the-
unknown-with-gpt-4-and-the-flipped-interaction-pattern-1f23acbc4c91
… -
Training Small Transformers on Arithmetic with Chain-of-Thought
By
–
8/ Teaching Arithmetics to Small Transformers – trains small transformers on chain-of-thought data to improve accuracy and convergence speed and highlights the importance of high-quality instructive data for rapidly eliciting arithmetic capabilities.
-
Synthetic surveying and personality simulation for customer development
By
–
A. Synthetic surveying / customer development is a cheaper alternative to doing the real thing, which is useful for ideation B. It makes customer development available even to people who don’t have large distribution C. The effective simulation of personality is a game changer
-
Synthetic Focus Groups: AI-Powered User Testing Tool
By
–
Synthetic Focus Groups Generate a synthetic audience and then user test ideas against them Cool repo from the community (
@venuv62
) -
Guide for LLM-Powered Chart and Image Generation Systems
By
–
An excellent guide on working with LLM-powered chart and image generation systems!!
-
Continue Claude 2 and GPT-4 Conversations on Poe
By
–
Continue either conversation: Claude 2: https://poe.com/s/x8lvyyxkX0mPzQbSPIJA … and GPT-4: https://poe.com/s/FFDSJLsQIsNGLU3Gdm00 …
-
GPT-4 Prompt Length Limits vs Code Interpreter Capabilities
By
–
I just pasted a prompt that GPT-4 complained was too long into Code Interpeter which happily accepted it
-
Lost in the Middle: Research Paper on LLM Context Processing
By
–
Paper: https://
arxiv.org/abs/2307.03172
Code: https://
nelsonliu.me/papers/lost-in
-the-middle
… Work from people at Stanford & UC Berkeley & Samaya AI. By @nelsonfliu
, Kevin Lin, @johnhewtt
, Ashwin Paranajape, @MicheleBevila20
, @Fabio_Petroni
, @percyliang