Amelia Wattenberger
Designer and engineer; formerly principal research engineer at GitHub Next; writes at wattenberger.com.
Amelia Wattenberger did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest x.com
What they believe
-
Chatbots are a terrible interface for large language models, because a text box has no affordances.
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.
wattenberger.comby 1 May 2023This on korrents
The bold line is korrents’ wording; the quote is theirs. These one: what they wrote before what they said aloud, one per source, newest first.
Beliefs
Korrents What they believe 4 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
Chatbots are a terrible interface for large language models, because a text box has no affordances.
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.
Why Chatbots Are Not the Future by 1 May 2023
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.
Good tools make it clear how they should be used. And more importantly, how they should not be used.
Why Chatbots Are Not the Future by 1 May 2023
Good tools let the user choose when to switch between implementing and evaluating; a chatbot forces the switch every few seconds and kills flow.
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.
Why Chatbots Are Not the Future by 1 May 2023
Show 1 more
We should want more tools and fewer operated machines; the real AI game changers will have little to do with plain content generation.
I want to see more tools and fewer operated machines - we should be embracing our humanity instead of blindly improving efficiency. And that involves using our new AI technology in more deft ways than generating more content for humans to evaluate. I believe the real game changers are going to have very little to do with plain content generation.
Why Chatbots Are Not the Future by 1 May 2023
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Where they publish
Site wattenberger.com Her essays on interfaces, data visualisation and AI, and her projects.
Link verified 6 Sept 2026.
x.com @Wattenberger Where her essays and prototypes get announced.
Recent
- 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 6 Oct 2026
- not even at 6 Oct 2026 spacejam.com
- how do we escape the chat trap? Maybe intelligent interfaces 6 Oct 2026 wattenberger.com
Show 17 more
- polished diagrams are shipped! go ahead and try them out would love to see fun examples from your workspaces 5 Oct 2026
- really enjoying how these interactions turned out! I put off making these examples until the last minute, but they're what finally convinced me to share. it's a just a small thing, but encourages the thinking that we can have tactile, more direct interfaces while leveraging our AI overlords 2 Oct 2026
- the potential to create entirely custom environments for creating is really only held back by our imagination it took one prompt to add an editing surface directly on the post itself. "let me edit the text and symbols with a keybinding and save it to disk" 1 Oct 2026
- we're back at the command line! there's so much good thinking to mine from from the last time we transitions from terminal -> gui. had some fun writing down a few thoughts would love to hear what you think 1 Oct 2026
- this is exactly why we have horizontal tabs for workspaces in https://t.co/2t7DWBiByX We've tried alll layouts and this one has felt the nicest in practice. We usually have a small set of things we're working on, and can tuck the rest away until we're ready. 29 Sept 2026
- can Jev! help organize my workspaces for me? 24 Sept 2026
- get yourself an agent harness that cares about diagrams. I'm sick of reading walls of text! 22 Sept 2026
- this is miles better than the models have done previously I've been trying this "redo these charts with this style" every few months 22 Sept 2026
- am I the only one who wants to know what my agents changed? 21 Sept 2026
- fun to see live confidence in different statements as the agents work! 17 Sept 2026
- how I imagine life as a scientist 11 Sept 2026
- playing with a lil dock to keep track of my agent friends 👀 10 Sept 2026
- okay I love this, but it's missing the entire 👉 point 👈 of the original video 3 Sept 2026
- it's in the air 3 Sept 2026
- your ui needs more deixis 2 Sept 2026 youtube.com
- the best explanation of this, for the curious 21 Aug 2026 jake.vision
- there's something rotten in the air when >90% of the replies to a tweet like this are mean spirited sure, it might not be your thing and it's easy to forget this box doesn't go straight into the void. but can we try to bring more kindness into the world? 15 Aug 2026
Link verified 6 Sept 2026. Recent items update automatically from the channel.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.