john_minsk

Great work. Thanks for inspiration.

Is it static collection or the designs were dynamically generated from concepts?

Super cool. Hope waitlist will move soon. I have a use case for it too.

are you the author? If so - what are your notes on using Jev in this scenario?

Why do you need to always modify the service? Once it is up and running and performs a function - don't touch it.

Interesting.

So one circuit essentially has 2 modes: 1 I do ActionA because I want to get GoalA 2 I do ActionA because it is my routine

What would be interesting to see is IF by activating this mechanism, mice start getting habits almost instantly for behaviors performed when this circuit was in the state#2. Correct me please.

His goal is to learn something. Your goal is to get information. Different scenarios.

Very cool!

At the top of the program you import Web Libraries. is it some standard Scheme web framework that you're using?

* ;; re-running this source bumps the generation; the old loop sees it ;; and lets go (js-eval "globalThis.__hero_gen = (globalThis.__hero_gen || 0) + 1") (define gen (js->number (js-get (js-global) "__hero_gen"))) (letrec ((tick (lambda _ (when (= gen (js->number (js-get (js-global) "__hero_gen"))) (frame!) (js-method (js-global) "requestAnimationFrame" tick))))) (js-method (js-global) "requestAnimationFrame" tick))

Is this the part where it is compiled?

I'm learning Clojure and using it in a vibe coding environment. AI hates brackets.

Well… your menu items will disappear behind it still in 2026. You would need an extra app for that…

But in terms of “noticing it” you are correct. You won’t pay attention after a day or two.

EDIT: this menu managing app will need permissios to make screen captures. So much for the privacy. Forgot to mention.

Amazing and Atrium looks great too! Where is it better to follow your work?

For Atrium you said that you save everything on disk. What usecases did you find toy have your old sessions saved?

How do you control it?

question: what will happen if orbit refuelling goes wrong? Won't it destroy everything in orbit?

Thank you.

Sorry for silly question. Is it a reason why after update I see new agent interface and no usual VSCode interface? I'm on Mac though.

I'm lost here by looking at 2.0 interface.

Could you please share?

For a lot of people in the world Europe = USA

In the future there shouldn't be any bugs. I'm not paying $20 per month to get non-secure code base from AGI.

what is this?

So let's say I run this with a lot of tasks.

- How many tasks/schedules have you tested? - What if some schedule has to run another schedule on demand. Can I clearly see it in a management view? - If you and me are running this. Can my task contact your task and be stay alive while another user finishes his task?

I strongly disagree. If the system is transparent enough and provides mechanisms for verification and control - No reason to distrust it. I would prefer a system where even in 20 years I can go online and check how my vote was counted in older elections - this way stealing my vote would be impossible.

The issue is how to preserve privacy...

Do you think prices will go up for mac?

What's the problem?

Really nice. Thanks for self promo! Will definitely keep an eye on your project.

What is the ideal final state you want to achieve? Do you agree that data capture is the main issue here?

My latest experiments:

2 days ago I started to capture screenshots of my mac every 5 seconds and later use it to approximately tell me what I'm doing. - a lot of issues with this approach.

Yesterday I setup ActivityWatch. It captures a lot of stuff from the get go. TBD if it can capture background YouTube video playing in addition to the active tab.

The main value I want to extract is to be able to see what was the plan vs what actually happened. And if I can make what actually happens closer to the plan - this is WIN.

But capturing what you are thinking of, what you are working on etc. - quite challenging and often happens offline, on the phone, another computer, messenger, email etc.

My quick take: companies were closing their data for decades and now it will bite them in their back - AI needs as full of a context as possible across devices, services and programs, to make AI as powerful as it can be and current architecture works against it. May be one day AI is so powerful that it will ETL all this data for itself, but for now it is painful to try to build something like this.

Real world might be boring, but very useful. Especially for companies that move boxes around, not fantasy characters.

That's exactly what I think will happen. 3D is endgame for AI. 3D models are deterministic objects that provide continuity, while AI does non-deterministic abstract generation(thinking) + plans action plan for these 3d models.

Recent news on major AI scientists starting "world AI" companies confirm this trend.

So 3D soon will become a very important tech even compared to today.

Why do you think so? As far as I can tell - a lot of GPU empowered data centers are being built

There is CAD Sketcher, which is an extension for Blender which could allow to unite both worlds.

I'd like to hear someone's perspective on how difficult it would be to unify OpenUSD and CAD file formats so that they are portable between programs?

OpenUSD got just 1 mention in the release notes. Also wondering what is the state of this feature.

May I ask your opinion, as industry insider, regarding what makes a good and bad OpenUSD support?

Do you think the next generation of Roblox will be a dominating games engine?

How is Evangelion still running if the series was finished and even alternative ending was produced?

Is there any good test scene that one can download to "test" capabilities of different software? Sorry if it is an ignorant question