Enough AI copilots, we need AI HUDs • Hacker News Board

Re: Enough AI copilots, we need AI HUDs

#61

Post by scottgg » Mon, Jul 28, 2025, 5:10 AM UTC

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…

WallabyJS does something along these lines, although I don’t think it is contextually understanding which tests to highlight

https://wallabyjs.com/

Re: Enough AI copilots, we need AI HUDs

#62

Post by bigyabai » Mon, Jul 28, 2025, 5:10 AM UTC

ravila4 wrote: post #60

elliotec wrote: post #57

Earlier quoted context omitted.

You just described what I do with my ultrawide monitor and laptop screen. I can be fully immersed in a game or anything and keep Claude in a corner of a tmux window next to a browser on the other monitor and jump in whenever I see it get to the next step or whatever.

It’s a similar idea, but imagine you could fire off a task, and go for a run, or do the dishes. Then be notified when it completes, and have the option to review the changes, or see a summary of tests that are failing, without having to be at your workstation.

I kinda do this today, with Alpaca[0]'s sandboxed terminal runner and GSConnect[1] syncing the response notifications to my phone over LAN.

[0] https://jeffser.com/alpaca/

[1] https://github.com/GSConnect/gnome-shell-extension-gsconnect

Re: Enough AI copilots, we need AI HUDs

#63

Post by andsoitis » Mon, Jul 28, 2025, 5:15 AM UTC

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…

> Imagine 10-100 tests that take Doesn’t seem like high ROI to run full suite of tests on each keystroke. Most keystrokes yield an incomplete program, so you want to be smarter about when you run the tests to get a reasonably good trade off.

Re: Enough AI copilots, we need AI HUDs

#64

Post by radres » Mon, Jul 28, 2025, 5:30 AM UTC

One of the simplest and best working applications of AI is the gpts living in your clipboard. Any prompt/workflow you have is assignable to a shortcut on demand and it pops up a chat window with response on demand. It's been game changing honestly.

Re: Enough AI copilots, we need AI HUDs

#65

Post by furyofantares » Mon, Jul 28, 2025, 5:33 AM UTC

radres wrote: post #64

One of the simplest and best working applications of AI is the gpts living in your clipboard. Any prompt/workflow you have is assignable to a shortcut on demand and it pops up a chat window with response on demand. It's been game changing honestly.

Can you elaborate on this?

Re: Enough AI copilots, we need AI HUDs

#66

Post by JimDabell » Mon, Jul 28, 2025, 5:37 AM UTC

skydhash wrote: post #54

JimDabell wrote: post #39

Earlier quoted context omitted.

I’m talking higher level than that. Think about the acceptance criteria you would put in a user story. I’m specifically responding to this: > 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. You don’t need to personally write code that mechanically iterates over every possible state to remain in the driver’s seat. You need to desc…

I think your perspective is heavily influenced by the imperative paradigm where you actually write the state transition. Compare that to functional programming where you only describe the relation between the initial and final state. Or logic programming where you describe the properties of the final state and where it would find the elements with those properties in the initial state. Those does not involves writing…

I didn’t mention state transitions. When I said “mechanically iterate over every possible state”, I was referring to writing tests that cover every type of input and output.

Acceptance criteria might be something like “the user can enter their email address”.

Tests might cover what happens when the user enters an email address, what happens when the user tries to enter the empty string, what happens when the user tries to enter a non-email address, what happens when the user tries to enter more than one email address…

In order to be in the driver’s seat, you only need to define the acceptance criteria. You don’t need to write all the tests.

Re: Enough AI copilots, we need AI HUDs

#67

Post by William_BB » Mon, Jul 28, 2025, 5:37 AM UTC

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…

There's no way this would work for any serious C++ codebase. Compile times alone make this impossible

I'm also not sure how LLM could guess what the tests should be without having written all of the code, e.g. imagine writing code for a new data structure

Re: Enough AI copilots, we need AI HUDs

#68

Post by furyofantares » Mon, Jul 28, 2025, 5:38 AM UTC

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.

Re: Enough AI copilots, we need AI HUDs

#69

Post by sitkack » Mon, Jul 28, 2025, 5:41 AM UTC

skydhash wrote: post #54

JimDabell wrote: post #39

Earlier quoted context omitted.

I’m talking higher level than that. Think about the acceptance criteria you would put in a user story. I’m specifically responding to this: > 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. You don’t need to personally write code that mechanically iterates over every possible state to remain in the driver’s seat. You need to desc…

I think your perspective is heavily influenced by the imperative paradigm where you actually write the state transition. Compare that to functional programming where you only describe the relation between the initial and final state. Or logic programming where you describe the properties of the final state and where it would find the elements with those properties in the initial state. Those does not involves writing…

Acceptance criteria describes the thing being accepted, it describes a property of the final state.

There is no prescriptive manner in which to deliver the solution, unless it was built into the acceptance criteria.

You are not talking about the same thing as the parent.

Re: Enough AI copilots, we need AI HUDs

#70

Post by digdugdirk » Mon, Jul 28, 2025, 5:43 AM UTC

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.

Interesting! I've often felt that we aren't fully utilizing the "low hanging fruit" from the early days of the LLM craze. This seems like one of those ideas.