Rendered at 12:28:06 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
lbreakjai 13 minutes ago [-]
I would pay good money for something like this on iPad. It wouldn't even need to be agent-driven, just a big "I want to make a bank transfer" button, that would launch the correct app and guide through the interface.
That would be a godsent for those of us with aging parents.
hn8726 6 minutes ago [-]
I tried to read the "Does it need Screen Recording or Accessibility?" part, but it's slopped to the point I have no clue what it's trying to say. But if it can draw on top of permission prompts, what's stopping it from drawing box that hides the "decline" button and changing the "approve" button copy?
isoprophlex 44 minutes ago [-]
Literally unusable as it is. Some minimal extra features this would need:
- rainbow dripping arrows
- angrily pointing arrows
- flame-surrounded text boxes with particle effects
- the ability for the agent to play airhorn.wav at max volume, overriding existing volume or mute settings
thih9 35 minutes ago [-]
At the risk of stating the obvious - let's not do that, the goal of this repo is to be useful and not to give agents the power of the `<blink>` tag.
koalacola 9 minutes ago [-]
Oh dear, they were making a joke.
ipsod 21 minutes ago [-]
under_construction.gif
arshxyz 32 minutes ago [-]
The README is geared towards technical people (complete with the HN screenshot) but when I see a tool like this all I can think of is how helpful this would be for my mom when I'm trying to tell her how to download and print a document over the phone
conception 5 minutes ago [-]
Honestly the giant arrow annotation Zoom has makes it worth any amount of money compared to the competition.
melvinroest 16 minutes ago [-]
My message to the world is that LLMs should be able to point anything they see in the application they're in or even the whole computer (if you give it that kind of access).
For web apps, WebMCP is a way where you can make a frontend way more discoverable to an LLM rather than that it is going to read all your code. I sometimes create this in my apps at home and sometimes in my apps at work and it makes LLM assistants way more usable. It also helps if they can highlight certain things of a visual.
We humans can do this too on paper. We can point at something, we can highlight something with a marker. Why not give an LLM these capabilities as well?
alansaber 21 minutes ago [-]
This might be goofy, but it underscores that there's potential for more visual agent UIUX than reading off a sidebar/opening modals.
melvinroest 1 minutes ago [-]
[dead]
vessenes 54 minutes ago [-]
Interesting. When I read the headline I imagined this would be a sort of thinking trace booster -- letting the agent focus its own attention on different parts of the screen. But this is cool in a different way. I bet agentic harnesses would find it useful for communicating with other agents / themselves as well.
FinnLobsien 46 minutes ago [-]
This could be great for documentation. Screenshots in docs are frequently useless because they show me a screen and say "click X" where I still have to search X visually. And I could just to dhat in the other tab I have open.
xyzsparetimexyz 43 minutes ago [-]
Seems like a pretyu useful way to help infants use desktop computers
ipsod 19 minutes ago [-]
Have you met users?
satyanash 1 hours ago [-]
Am I missing something here?
What terminal / agentic workflows spawn the demonstrated dialogue boxes that require the User to click/reject the action? Aren't most such flows actually inline UIs? And finally, if the core issue is that these confirmation boxes are tied to the terminal that triggered them, which does not autofocus, what's the point of said "big arrow" that is also lurking behind without focus?
If the said "big arrow" automatically gains focus, isn't the real fix here to just make the dialogue boxes themselves gain focus automatically? Both are similarly disruptive anyway.
inanutshellus 57 minutes ago [-]
The first example (of HN) is the one that feels like it has the most potential to me.
"Teach me to use this app myself" kinda stuff. Guiding agent rather than doing agent.
Honestly, @franze, if you're reading this, maybe update your screenshots with that bent (showing us an agent in tutorial mode on some complicated app)?
TekMol 57 minutes ago [-]
Swift, Shell, Python and Objective-C
Does one need 4 programming languages to draw something on a mac?
sitzkrieg 55 minutes ago [-]
welcome to zombocom. err i mean modern HN :-(
ex-aws-dude 13 minutes ago [-]
If you can’t even take the time to understand what you’re clicking why even go through the formality of “approving”
lapestenoire 1 hours ago [-]
I love it.
ForHackernews 1 hours ago [-]
"and they keep hitting the same wall, the part that only a human may do"
Grim. If you're just there to click sudo buttons for the bot, you might as well give it root access and be done.
franze 59 minutes ago [-]
Claude refuses to do certain actions (enter passwords, change security settings, create new accounts on external services) even in Yolo mode running as sudo. (I tested it all on its own mac machine)
gwerbin 56 minutes ago [-]
You can add custom auto-mode classifier rules and even disable the built-in ones, if you want to live on the edge like this.
1 hours ago [-]
DonHopkins 30 minutes ago [-]
Ha ha, I love it! I wrote a pointing hand annotation overlay in PostScript in 1989 for NeWS and the PSIBER Space Deck's Pseudo Scientific Visializer:
% @(#)handy.ps
%
% Handy Pointer
% Copyright (C) 1989.
% By Don Hopkins. (don@brillig.umd.edu)
% All rights reserved.
Yet your post is even lower effort and quality, with much less useful information, and a tragic waste of everyone's time.
As a human stochastic parrot, don't you find it embarrassing and humbling to be so easily outdone by an LLM?
nixosbestos 51 minutes ago [-]
What a time to be a radical centrist - the AI haters seem out of touch, the AI thought leaders can't stop huffing their farts and being condescending, and somehow this is on the top of HN. What a silly time.
That would be a godsent for those of us with aging parents.
- rainbow dripping arrows
- angrily pointing arrows
- flame-surrounded text boxes with particle effects
- the ability for the agent to play airhorn.wav at max volume, overriding existing volume or mute settings
For web apps, WebMCP is a way where you can make a frontend way more discoverable to an LLM rather than that it is going to read all your code. I sometimes create this in my apps at home and sometimes in my apps at work and it makes LLM assistants way more usable. It also helps if they can highlight certain things of a visual.
We humans can do this too on paper. We can point at something, we can highlight something with a marker. Why not give an LLM these capabilities as well?
What terminal / agentic workflows spawn the demonstrated dialogue boxes that require the User to click/reject the action? Aren't most such flows actually inline UIs? And finally, if the core issue is that these confirmation boxes are tied to the terminal that triggered them, which does not autofocus, what's the point of said "big arrow" that is also lurking behind without focus?
If the said "big arrow" automatically gains focus, isn't the real fix here to just make the dialogue boxes themselves gain focus automatically? Both are similarly disruptive anyway.
"Teach me to use this app myself" kinda stuff. Guiding agent rather than doing agent.
Honestly, @franze, if you're reading this, maybe update your screenshots with that bent (showing us an agent in tutorial mode on some complicated app)?
Does one need 4 programming languages to draw something on a mac?
Grim. If you're just there to click sudo buttons for the bot, you might as well give it root access and be done.
PSIBER Space Deck and Pseudo Scientific Visualizer Demo:
https://youtu.be/_fqCeuue5Ac?t=213
The Shape of PSIBER Space: PostScript Interactive Bug Eradication Routines — October 1989:
https://medium.com/@donhopkins/the-shape-of-psiber-space-oct...
~guywithnopowertodisallowit
As a human stochastic parrot, don't you find it embarrassing and humbling to be so easily outdone by an LLM?