Prompting Considered Harmful | Communications of the ACM
"Role prompting"... telling the model to assume a role has never been a good way to elicit capabilities/style/etc.
For instance, if you ask one of the Claude models to simulate Bing Sydney, assuming you can get it to consent, the simulation will probably be very inaccurate. But if you use a prompt that tricks them into predicting it indirectly (https://t.co/wJEAlPgfz6... See more
A Systematic Approach to Prompts
BJ PhD Fogg • Tiny Habits: The Small Changes That Change Everything
large prompts will prove to be an anti-pattern. They go against the common wisdom in software engineering.
Write small, testable, functions.
Imagine a world where LLMs are used for small, incremental steps.
That’s how engineering works. It’s taking a large problem and breaking it down into smaller problems.
This is how you test, validate and evaluate ... See more
Write small, testable, functions.
Imagine a world where LLMs are used for small, incremental steps.
That’s how engineering works. It’s taking a large problem and breaking it down into smaller problems.
This is how you test, validate and evaluate ... See more
Feed | LinkedIn
The more different your real-world problems are from the data you used to train the system, the less likely the system is to be reliable.