DataRobot for generative AI is here! The new offering builds on the DataRobot AI Platform with comprehensive capabilities to build, deploy, and manage your generative and predictive AI projects. Seamlessly integrate LLMs, vector databases and prompting strategies with your
PROMPT ENGINEERING
-
Custom Instructions Tips: How Did You Create Yours?
By
–
Who else has clever custom instructions? +how did you come up with them
-
ChatGPT Cheat Sheet: Essential Tools and Strategies for Marketing
By
–
Generative #AI and #ChatGPT are transforming #marketing, but where do you start? Check out this excellent ChatGPT 'Cheat Sheet' by Max Rascher! It's packed with tools, prompts, tips, roles, and strategies to help you use ChatGPT more effectively. #generativeAI @ingliguori
-
Tip: type /help for relevant resources
By
–
6. If you're stuck on a particular problem, you can type /help, and the ChatGPT will suggest relevant resources based on your inquiry.
-
ChatGPT allows coding without leaving messenger via /code command
By
–
1. ChatGPT allows you to code without leaving the messenger interface. To start a new conversation, simply type /code, and you're good to go.
-
10 tips & tricks to master ChatGPT as a code interpreter
By
–
The most valuable secret weapon for developers in 2023. ChatGPT is a code interpreter with endless uses. Let's take a look at 10 tips & tricks to master it:
-
Generic AI Models Struggle With Brand-Specific Performance
By
–
It also doesn’t mean it’s on brand (your tone, style, etc) or actually going to perform well (since most models are generalists, not trained on your data or top-performing assets).
-
Simple Prompting Techniques Achieve 49 F1 Score Baseline
By
–
2/ We started with simple prompting — tell the model what you're looking for and how to format its responses. This catches a lot of the low hanging fruit (~49 F1), but still needs refinement.
-
Data-Centric Prompt Engineering: Iterative Model Error Refinement
By
–
3/ We then began data-centric prompt engineering, iteratively identifying model error modes and addressing them in the prompt where possible, either with added detail in the prompt or adding in-context examples (~68 F1).
-
Fine-tuning and Prompt Engineering Outperform GPT-4 Baseline
By
–
1/ Prompt engineering LLMs is valuable, but used alone leaves many points on the table. See how we combine prompt engineering and fine-tuning to create a specialized model that outperforms prompted GPT-4 by 15 to 34 points on a real-world extraction task! https://
snkl.ai/pro