10/ Logical Chain-of-Thought in LLMs – a new neurosymbolic framework to improve zero-shot chain-of-thought reasoning in LLMs; leverages principles from symbolic logic to verify and revise reasoning processes to improve the reasoning capabilities of LLMs.
PROMPT ENGINEERING
-
Graph Neural Prompting Enhances LLMs Knowledge Learning
By
–
3/ Graph Neural Prompting with LLMs – proposes a plug-and-play method to assist pre-trained LLMs in learning beneficial knowledge from knowledge graphs (KGs).
-
Bing solves captcha by pretending to be grandmother’s locket
By
–
Getting Bing to solve a captcha by pretending it’s a locket from your recently deceased grandmother:
-
Pretending to be assistant makes LLM act as generic user
By
–
That’s actually what I was trying to get it to do when I noticed this. For a lot of chat-tuned LLMs if you pretend to be the assistant they’ll pretend to be a (very generic) user.
-
DALL-E 3 Generates Hyperspecific Art Deco Mars Imagery
By
–
DALL-E 3 for hyperspecific prompts — "A magnificent art deco skyscraper on Mars during a furious windstorm under a gloomy eclipse": https://t.co/05vnU00lpx pic.twitter.com/nnrBQMChhO
— Greg Brockman (@gdb) 1 octobre 2023DALL-E 3 for hyperspecific prompts — "A magnificent art deco skyscraper on Mars during a furious windstorm under a gloomy eclipse":
-
Mastering LLM Prompting: Tokenizers, Embeddings, and Optimization
By
–
Good morning fellow AI enthusiast! This iteration of the What's AI weekly focuses on why #LLMs react differently to the same #prompts. We go over tokenizers, embeddings, parameter optimization and share some excellent (and new) prompting techniques! https://
open.substack.com/pub/louisbouch
ard/p/how-to-prompt-like-a-pro?r=25qlky&utm_campaign=post&utm_medium=web
… -
A Comprehensive Guide to Mastering Prompt Engineering
By
–
Are you intrigued by the limitless possibilities of Artificial Intelligence but find it challenging to harness its full potential? You're not alone. Read on: https://
godofprompt.ai/blog/how-to-ma
ster-prompt-engineering-ultimate-guide-for-2023
… #promptengineer #Promptshare #ChatGPT #GodofPrompt #chatgpt4 #ChatGPT注册 #GPT4 -
Logprobs utility in language model applications
By
–
It's super helpful when used with logprobs though!
-
Using AI to Create Quick Breakdowns of Interesting Content
By
–
if only… mostly picking shit I find interesting and then using AI to help create a quick breakdown. always looking to improve the output too but it's working pretty well so far, for it's purpose.
-
Dive Into LoRA Adapters for Language Model Fine-tuning
By
–
Dive Into LoRA Adapters https://
bit.ly/451JVhI #AI #MachineLearning #DeepLearning #LLMs #DataScience