10 ChatGPT prompts that can turn your side hustle into a 6-figure business:
PROMPT ENGINEERING
-
Anthropic Launches Test Case Generation and Prompt Evaluation
By
–
Test case generation and output comparison features are available to all users today. Get started on https://
console.anthropic.com or read more on https://
anthropic.com/news/evaluate-
prompts
…. -
Side-by-side prompt comparison and expert grading feature
By
–
We’ve also added the ability to compare the outputs of two or more prompts side by side. As you iterate on different versions of the prompt, your subject matter experts can compare responses and grade them on a 5-point scale.
-
Evaluate Tab Automates Test Case Creation for Prompts
By
–
The new Evaluate tab enables you to automatically create test cases to evaluate your prompt against real-world inputs. Modify your test cases as needed, then run all of them in one click.
-
Anthropic Console Adds Prompt Generation and Side-by-Side Testing
By
–
We've added new features to the Anthropic Console.
— Anthropic (@AnthropicAI) 9 juillet 2024
Claude can generate prompts, create test variables, and show you the outputs of prompts side by side. pic.twitter.com/H6THdoja7ZWe've added new features to the Anthropic Console. Claude can generate prompts, create test variables, and show you the outputs of prompts side by side.
-
AI Agent for Self-Correcting Text-to-SQL Queries
By
–
One more cookbook:
Agent for self-correcting Text-to-SQL What if the query generated by your Text-to-SQL pipeline is correct SQL but returns wrong results? We need to add a critique step That's very simple with an agent!
Check out the notebook! -
Using Custom GPTs for News Headline Writing
By
–
Headline writing is a very nice AI use case for news publishers. A Custom GPT works perfectly for this purpose I was experimenting with it as well. Works super well for me.
-
Project Names as Shorthand for Complex AI Concepts
By
–
To add to that, it’s awesome that you can use project names as short-hand for complex ideas. For example, you could ask for “a BabyAGI that uses Multi-On to execute tasks” which is a complex but clear idea in a few words.
-
Better Performance Through Right Customization
By
–
Seeing performance way better when customizing right now
-
Claude Sonnet 3.5 enables BabyAGI implementation without frameworks
By
–
Apparently Claude Sonnet 3.5 can code you your own implementation of BabyAGI Starting here and iterating on this with Claude should be a good start/exercise for anyone looking to build an autonomous agent without relying on external frameworks.