That really undermines the author's claims. This article feels dishonest in it's claim that "small, cheap, open-weights models ... recovered much of the same analysis."

Hard parts:

– Getting the model to point to specific UI elements

– Keeping it coherent across multi-step workflows (“Help me create a sword in Tinkercad”)

– Preventing the infinite mirror effect and confusion between window vs full-screen sharing

– Keeping voice → screenshot → inference → voice latency low enough to feel conversational

We packaged it as “Clippy” for fun, but the real experiment is letting a model tool-call fresh screenshots to help it gather more context.

One practical use case is remote tech support — I'm sending this to my mom next time she calls instead of screen sharing.

Curious what breaks.

Comments URL: https://news.ycombinator.com/item?id=47429822

Points: 5

# Comments: 0

From what I can tell, there is no longer any way to easily get to the underlying web page that was referenced in generating its answer to my question.

This feels like a pretty meaningful step backwards. Am I missing something?

Comments URL: https://news.ycombinator.com/item?id=47247891

Points: 6

# Comments: 4

I think the main problem with attempting to document this is that the system would not be running off of it. Your infrastructure document is automatically read and drives the deploy (or whatever). But if you want to make a change to a human’s responsibilities, you don’t get the simplicity of updating your organization documentation and clicking “execute.” So this new documentation you propose would always be lagging documentation rather than the actual driver of organizational behavior.

But! What if it was? What if all the managers in an organization were AI systems? They would read diff in the org chart and it initiated the communication to the respective human employees.

I could imagine testing this in a coffee-shop level business right now in which the LLM is probably capable of all the strategy and management decisions needed to effectively run it, operating within the constraints of policies and procedures all cleanly laid out in documentation.

Claude writes a bunch of new code and I’ll tell it, “Before I review this code, make sure all tests adhere to the guidance of @tests.md” (you can probably make this a slash command too)

I find that if I put these instructions in the system prompt, far down in a conversation that’s used lots of the context window, they will only loosely be followed. But when I tag it in like this, Claude will strongly and thoughtfully follow the guidance and examples I’ve written up about how I want my tests.

Volumetric displays: https://youtu.be/na7pvihXhYs?si=cIWIk2yrv-WVbe4x

Physically adaptive desktop: https://tangible.media.mit.edu/project/transform-as-dynamic-...

I'm eager to learn about ones I've never seen!

I know I’m highly unusual amongst my friends. I’ve also found it odd that the more knowledgeable someone is about tech, the more scared they are of their kids using the internet.

But just like riding a bike and swimming in a pool are extremely dangerous, yet I encourage my kids to do both of these things and instead just educate them about risks. Similarly, I think the benefit-vs-risk of the internet is FAR better than a bike & pool, so I just educate them.

(In line with Gibson’s famous quote that, "The future is already here—it's just not evenly distributed.")

Comments URL: https://news.ycombinator.com/item?id=46518622

Points: 3

# Comments: 1

However, I still think there's something to be said for movies attempting to build UIs that have a strong aesthetic and elicit an emotional response, whereas production apps feel so flat and boring, in comparison.

I still wonder why we aren't seeing people try to push the envelope stylistically to "wow" users.

This might be a clearer articulation of what I'm trying to get at with my question...

Maybe there is some true limitation inherent in this style UI which causes them to stay as mere experiments / novelty?

I'm thinking about demos like this which I've seen go by HN over the years (I'm not involved in any of these):

LCARS demo: https://www.mewho.com/ritos/

Tron-like terminal: https://github.com/GitSquared/edex-ui

Sci-fi UI components: https://github.com/arwes/arwes

And I've long been a fan of designers like gmunk doing UI work for film: https://gmunk.com/Oblivion-GFX

But I'm genuinely confused why the actual UIs we all use on a daily basis are all so derivative of one another when the space of UI possibilities is so vast.

Comments URL: https://news.ycombinator.com/item?id=46500724

Points: 2

# Comments: 5

Try it here, no sign up: https://taskmaster.keithschacht.com

I find it useful to talk aloud to figure out priorities. With this, I can just ramble, “Mark that first task as done. Actually undo that. Add a task to proofread it. Move that to the top…”

It’s built on LiveKit with a Rails web UI. It listens continuously, maps speech to tool calls, and keeps full task-list state so it understands vague references like “the third item” or “the one with my kids.”

Voice feels much faster for input, but visual feedback is still higher bandwidth for output. This is intentionally rough—a demo focused on interaction, not features.

Curious how the interaction model feels for people?

Code: https://github.com/keithschacht/taskmaster

Comments URL: https://news.ycombinator.com/item?id=46403351

Points: 5

# Comments: 1

I’ve found it much more useful in life to always assume I’m not doing something to its full potential.