What Amelia Wattenberger thinks about chat interfaces
Designer and engineer; formerly principal research engineer at GitHub Next; now at Adept; writes at wattenberger.com.
Amelia Wattenberger did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Only Amelia Wattenberger on chat interfaces. See everyone on chat interfaces
3 dated positions, 2023, in their own words. Our reading of what Amelia Wattenberger has said — not written or endorsed by them.
-
by
Their wordsGood tools make it clear how they should be used. And more importantly, how they should not be used.
-
by
Their wordsGood tools let the user choose when to switch between implementation and evaluation. When I work with a chatbot, I'm forced to frequently switch between the two modes.
-
by
Our readingChatbots are a terrible interface for large language models, because a text box has no affordances.
Their wordsHopefully I've convinced you that chatbots are a terrible interface for LLMs. Or, at the very least, that we can add controls, information, and affordances to our chatbot interfaces to make them more usable.