Amelia Wattenberger
Person on 3 sites
Amelia Wattenberger is a designer and engineer who works on novel interfaces, data visualisation and AI tools.
-
3 facts on wiqqi (opens wiqqi.app)
- GitHub Next: Principal research engineer; prototypes include Copilot for Docs, GitHub Blocks and Code Atlas (opens wiqqi.app)
- Book: Fullstack D3 and Data Visualization (book and course) (opens wiqqi.app)
- Essays: Interactive essays on interfaces and AI, e.g. Our interfaces have lost their senses (opens wiqqi.app)
-
2 channels on ppll (opens ppll.app)
-
x.com: @Wattenberger (opens x.com)
“we need ways to make it clear what is… - explicitly specified - hinted at - an agent assumption any amount of the above is fine, but once code is in the codebase there’s no way to tease out what’s what”
- Site: wattenberger.com (opens wattenberger.com)
-
x.com: @Wattenberger (opens x.com)
-
4 beliefs on korrents (opens korrents.com)
-
Chatbots are a terrible interface for large language models, because a text box has no affordances. (opens korrents.com)
“Hopefully 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.”
-
Good tools make it clear how they should be used and how they should not; a chat box looks the same as a search box, a login form and a credit card field. (opens korrents.com)
“Good tools make it clear how they should be used. And more importantly, how they should not be used.”
-
Good tools let the user choose when to switch between implementing and evaluating; a chatbot forces the switch every few seconds and kills flow. (opens korrents.com)
“Good 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.”
-
Chatbots are a terrible interface for large language models, because a text box has no affordances. (opens korrents.com)