Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Enough AI copilots, we need AI HUDs

geoffreylitt.com

Post reply on HN
Print view View original

111–120 of 290 posts

Re: Enough AI copilots, we need AI HUDs

#111

Post by teoremma »

furyofantares wrote: post #68

I'm very curious if a toggle would be useful that would display a heatmap of a source file showing how surprising each token is to the model. Red tokens are more likely to be errors, bad names, or wrong comments.

We explored this exact idea in our recent paper https://arxiv.org/abs/2505.22906

Turns out this kind of UI is not only useful to spot bugs, but also allows users to discover implementation choices and design decisions that are obscured by traditional assistant interfaces.

Very exciting research direction!

Re: Enough AI copilots, we need AI HUDs

#112

Post by simianwords »

I believe this is the framework vs library debate but in a different context. HUD is like me using a library of AI enabled tools. The human agency is given more importance here - they decide how to use the tools to suit their purpose.

Copilot is more like a framework where an AI system exists which tells me what to do (a bit like the inverse of a library).

Re: Enough AI copilots, we need AI HUDs

#113

Post by JimDabell »

motorest wrote: post #100
JimDabell wrote: post #88

Earlier quoted context omitted.

I know about BDD frameworks. I’m talking higher level than that.

> I know about BDD frameworks. I’m talking higher level than that. What level do you think there is above "Given I'm logged in as a Regular User When I go to the front page Then I see the Profile button"?

The line you wrote does not describe a feature. Typically you have many of those cases and they collectively describe one feature. I’m talking about describing the feature. Do you seriously think there is no higher level than given/when/thens?

Re: Enough AI copilots, we need AI HUDs

#115

Post by bravesoul2 »

energy123 wrote: post #53
hi_hi wrote: post #8

Doesn't it all come down to "what is the ideal interface for humans to deal with digital information"? We're getting more and more information thrown at us each day, and the AIs are adding to that, not reducing it. The ability to summarise dense and specialist information (I'm thinking error logs, but could be anything really) just means more ways for people to access and view that information who previously wouldn't…

The designers of 6th gen fighter jets are confronting the same challenge. The cockpit, which is an interface between the pilot and the airframe, will be optionally manned. If the cockpit is manned, the pilot will take on a reduced set of roles focused on higher-level decision making. By the 7th generation it's hard to see how humans will still be value-add, unless it's for international law reasons to keep a human in…

We will get to the dream of Homer Simpson gorging on donuts and "operating" a nuclear power plant.

Re: Enough AI copilots, we need AI HUDs

#116

Post by alwa »

afro88 wrote: post #107

A HUD is an even more "confident" display of data than text though. What do you do with a HUD that hallucinates? Is there a button on each element that shows you sources?

Night-vision optics come to mind: prone to noise and visual artifacts, and especially strange under certain edge conditions. Some of their specs tend to be strictly inferior to a Mark I Eyeball—narrow FOV, limited focusing power, whatever else.

But an operator learns to intuit which aspects to trust and which to double-check. The fact that it’s an “extra sense” can outweigh the fact that it’s not a perfect source of truth, no? Trust the tech where it proves useful to you, and find ways to compensate (or outright don’t use it) where it’s not.

Re: Enough AI copilots, we need AI HUDs

#117

Post by thbb123 »

energy123 wrote: post #53
hi_hi wrote: post #8

Doesn't it all come down to "what is the ideal interface for humans to deal with digital information"? We're getting more and more information thrown at us each day, and the AIs are adding to that, not reducing it. The ability to summarise dense and specialist information (I'm thinking error logs, but could be anything really) just means more ways for people to access and view that information who previously wouldn't…

The designers of 6th gen fighter jets are confronting the same challenge. The cockpit, which is an interface between the pilot and the airframe, will be optionally manned. If the cockpit is manned, the pilot will take on a reduced set of roles focused on higher-level decision making. By the 7th generation it's hard to see how humans will still be value-add, unless it's for international law reasons to keep a human in…

> keep a human in the loop before executing the kill chain, or to reduce Skynet-like tail risks in line with Paul Christiano's arms race doom scenario.

It is a little known secret that plenty of defense systems are already set up to dispense of the human in the loop protocol before a fire action. For defense primarily, but also for attack once a target has been designated. I worked on protocols in the 90's, and this decision was already accepted.

It happens to be so effective that the military won't bulge on this.

Also, it is not much worse to have a decision system act autonomously for a kill system, if you consider that the alternative is a dumb system such as a landmine.

Btw: while there always is a "stop button" in these systems, don't be fooled. Those are meant to provide semblance of comfort and compliance to the designers of those systems, but are hardly effective in practice.

Re: Enough AI copilots, we need AI HUDs

#119

Post by stahorn »

AlotOfReading wrote: post #22
hi_hi wrote: post #8

Doesn't it all come down to "what is the ideal interface for humans to deal with digital information"? We're getting more and more information thrown at us each day, and the AIs are adding to that, not reducing it. The ability to summarise dense and specialist information (I'm thinking error logs, but could be anything really) just means more ways for people to access and view that information who previously wouldn't…

Websites were a way to get authoritative information about a company, from that company (or another trusted source like Wikipedia). That trust is powerful, which is why we collectively spent so much time trying to educate users about the "line of death" in browsers, drawing padlock icons, chasing down impersonator sites, mitigating homoglyph attacks, etc. This all rested on the assumption that certain sites were auth…

I imagine there will be the same problems as with Facebook and other large websites, that used their power to promote genocide. If you're in the mood for some horror stories:

https://erinkissane.com/meta-in-myanmar-full-series

When LLM are suddenly everywhere, who's making sure that they are not causing harm? I got the above link from Dan Luu (https://danluu.com/diseconomies-scale/) and if his text there is anything to go by, the large companies producing LLMs will have very little interest in making sure their products are not causing harm.

Re: Enough AI copilots, we need AI HUDs

#120

Post by willtemperley »

callc wrote: post #25
cadamsdotcom wrote: post #4

Love the idea & spitballing ways to generalize to coding.. Thought experiment: as you write code, an LLM generates tests for it & the IDE runs those tests as you type, showing which ones are passing & failing, updating in real time. Imagine 10-100 tests that take The tests could appear in a separated panel next to your code, and pass/fail status in the gutter of that panel. As simple as red and green dots for tests t…

Humans writing the test first and LLM writing the code is much better than the reverse. And that is because tests are simply the “truth” and “intention” of the code as a contract. When you give up the work of deciding what the expected inputs and outputs of the code/program is you are no longer in the drivers seat.

Yes this is fundamental to actually designing software. Still, it would be perfectly reasonable to ask "please write a test which gives y output for x input".
Post reply on HN