PROMPT ENGINEERING - AI Dynamics

AI integration into spreadsheets using chat instructions in plain English

By

–

28 January 2023 1h19

AI integration into spreadsheets: http://
Akkio.com – reformat all types of .csv data by chatting instructions in plain english. -No coding
-No formulas Excel was long overdue for an update. This is slick.

→ View original post on X — @aibreakfast

28 January 2023

SQL Database Agent Optimization via Prompt Engineering

By

@langchain

–

27 January 2023 18h55

yes new ones! see the thread for an example of an agent optimized (via the prompt) for interacting with a sql db

→ View original post on X — @langchain

27 January 2023

Robustness to prompts for specific writing styles via instruction or k-shot

By

@goodside

–

27 January 2023 7h26

Is this robust to prompts that request specific writing styles, through either instruction or k-shot demonstration of human writing?

→ View original post on X — @goodside

27 January 2023

AI Tool Generates LinkedIn Posts Automatically

By

@futurepedia_io

–

27 January 2023 2h00

https://
futurepedia.io/tool/viral-pos
t-generator
… generates cringey linkedin posts for you using AI #AI #ChatGPT

→ View original post on X — @futurepedia_io

27 January 2023

ChatGPT as Full Self-Driving for Content Creation

By

@learnopencv

–

27 January 2023 0h55

#ChatGPT is the #FSD of content creation. Fun but use with extreme caution

→ View original post on X — @learnopencv

27 January 2023

Testing Email Classifier on Unseen Data Samples

By

@saboo_shubham_

–

26 January 2023 16h15

Step 4: Test your email classifier on unseen input data samples to validate if everything is working properly.

→ View original post on X — @saboo_shubham_

26 January 2023

Prompt Engineering as Systems Engineering: LLM Workflow Abstraction

By

@swyx

–

26 January 2023 5h45

“Prompt engineering looks more like a systems engineering problem, not a machine learning one.” i like the concept of an “LLM friendly workflow engine”. concats all my recent professional interests into one sorely needed abstraction

→ View original post on X — @swyx

26 January 2023

Instruction Tuning as an Emergent Ability in Large Language Models

By

@_jasonwei

–

25 January 2023 20h36

One of the most interesting emergent abilities IMO is instruction tuning. Anthropic and Flan-LaMDA suggest that zero-shot performance can improve from RLHF and NLP benchmark instruction tuning (although text-davinci usually loses to code-davinci). https://
arxiv.org/abs/2204.05862

→ View original post on X — @_jasonwei

25 January 2023

GPT as Backend: LLM as English Interpreter for Development

By

@karpathy

–

25 January 2023 19h15

"GPT is all you need for backend". This was the most inspirational project from the hackathon over the weekend, hard to stop thinking about. LLM is a kind of equivalent of the Python interpreter, except it interprets English, and has knowledge and common sense.

→ View original post on X — @karpathy

25 January 2023