Tools
Search
Import
Library
Explore
Videos
Channels
Figures
Atmrix
About
Tools
Search
Import
Library
Explore
Videos
Channels
Figures
Atmrix
About
Go Back
A
Anthropic Cast
09/06/24
@ Anthropic
I often define new concepts when prompting to convey nuanced ideas clearly to the model.
Video
A
AI prompt engineering: A deep dive
@ Anthropic
09/06/24
Related Takeaways
AA
Amanda Askell
09/06/24
@ Anthropic
As models improve, it's often more effective to communicate the specific task directly rather than using metaphors or role-based prompts.
A
Anthropic Cast
09/06/24
@ Anthropic
When prompting, I try to give examples that are not too similar to the data the model will see, to avoid overly consistent responses.
A
Anthropic Cast
09/06/24
@ Anthropic
When prompting, it's important to give the model an 'out' for unexpected inputs, allowing it to indicate uncertainty when necessary.
A
Anthropic Cast
09/06/24
@ Anthropic
The skill of prompting is about introspection, understanding what you want, and making yourself legible to the model.
AA
Amanda Askell
09/06/24
@ Anthropic
A good prompt engineer must communicate clearly, iterate on prompts, and anticipate potential misinterpretations by the model.
A
Anthropic Cast
09/06/24
@ Anthropic
A good prompt engineer should be able to step back from their own knowledge and communicate the necessary information clearly to the model.
SS
Sander Schulhoff
06/19/25
@ Lenny's Podcast
Including additional information or context in prompts significantly improves the model's understanding and output quality.
SS
Sander Schulhoff
06/19/25
@ Lenny's Podcast
Chain of thought prompting, where you instruct the model to think step-by-step, is less necessary with modern reasoning models but can still be useful in some cases. If you're running thousands or millions of inputs through your prompt, you'll still need to use classical prompting techniques to make your prompt more robust.
SS
Sander Schulhoff
06/19/25
@ Lenny's Podcast
When providing context, it's often best to place it at the beginning of the prompt to ensure the model retains focus on the task.