I've been using ChatGPT to generate emails for potential interviewees to discuss ChatGPT, and also using ChatGPT to generate questions for them on the fly. Not sure this is saving me any time or effort, and the results are often laughable. But what a time to be alive…
PROMPT ENGINEERING
-
Claude identifies ambiguity in apple-box riddle; GPT-3 misses it
By
–
Claude answers that the problem is too vague, because it’s not stated whether the apple is in the red box, and explains how to get the apple in both scenarios. GPT-3 doesn’t recognize this. I’m sure you could k-shot it with other riddles that contain irrelevant distractor info.
-
Acknowledging hallucinations in AI models while noting improvements
By
–
To be fair, there are still cases of hallucination. We admit to it too in our tweets. Just so turns out that @zan2434 was detailed enough in his queries and it worked fine. As the product and these models evolve, things should get better.
-
Prompt injection is a U-shaped scaling phenomenon
By
–
Prompt injection is a U-shaped scaling phenomenon!
-
English Becomes the Hottest New Programming Language
By
–
The hottest new programming language is English
-
Appreciation for Well-Written COT Prompting Article
By
–
An interesting read on COT Prompting, well-written Shubham
-
LangChainHub Launches Platform for Sharing Prompts and Agents
By
–
One new thing we've been testing out is the idea of a "LangChainHub" – a place to share and discover prompts, chains, and agents. We officially launched it today with just prompts – hope to add chains and agents in soon. If you have feedback or suggestions please let us know!
-
Google Research on Chain of Thought Prompting Explained
By
–
Read this amazing masterpiece by google research to deepen your understanding on the chain of thoughts prompting – https://
ai.googleblog.com/2022/05/langua
ge-models-perform-reasoning-via.html
… -
Chain of Thought Frameworks for Advanced AI Solutions
By
–
Here are some innovative frameworks leveraging Chain of thoughts prompting to enable advanced AI solutions: 1. @langchain 2. @dust4ai Feel free to add more if you come across any and share your experience!
-
Chain of Thought Prompting Advances Language Model Reasoning
By
–
With Chain of Thought prompting, language models of sufficient scale can solve complex reasoning problems that are not solvable with standard prompting methods. It is a huge step forward in AI, making LLMs more interpretable and better equipped to tackle complex problems.