jv22222

Agree.

Creating products with AI is like creating a tightly packed ball of wool. Then, to try to understand what happened you have to somehow pick a strand and pull it out to have a look. Very difficult with tightly packed wool.

I've run some experiments in the past month that get me closer to being able to work with this opaque bundle.

It's the main thing I think about every day, how to solve this problem.

Came to say the same thing. Experts in any field have a huge unlock from AI.

Nooooo! Sigh. RIP JCD :(

I was very lucky to get a chance to interview him on our podcast back in 2010 [1]. He of course was very funny and insightful.

So kind of him to even come on our unknown show.

I used to love listening to him in early No Agenda [2] talking about his takes on all sorts of worldly things especially fine dining, spices, and all the famous people he'd had run-ins with.

[1] https://techzinglive.com/episode/6bc8086b/50-tz-interview-th...

[2] https://www.noagendashow.net/

Yeah, I have been thinking exactly the same. Makes all the sense in the world and is inevitable as far as I can see.

https://news.ycombinator.com/item?id=48464958

> parakeet on a mac which transcribes all my uh's and aahs

You should be able to fix this by playing with the mic speech floor. It happens when to much ambient stuff slurps in.

It's actually gaslighting you, you don't say that many ums and ahs ;)

Nice work on making a self hosted version I think that kind of privacy is something a lot of people want these days.

lol. type CMD- a few times. The human text jumps out as you shrink it!

I'm working on a Mac OS memory app for AI. Not quite ready to share the link, but just wanted to put the periscope above the water.

4 years doing this before AI. Then I felt my tool was not quite right for the AI environment. Now I'm building something else with AI.

This is weird but I think I like to focus wherever I feel needs polish.

So, making a real time collaborative tool from scratch there was a lot of deep work in things like sockets, queues, memory structures, etc. That's just what needed attention.

Right now I'm building a memory app for AI.

So far I haven't spent much time looking at code on the swift side of things. But I have spent a lot of time up front working on domain driven design, screaming architecture, and module based design.

I think with AI the polish is in deep QA, design taste, running trace logs and constantly asking it to do html diagrams of the architecture and such.

ngl I miss "knowing what's going on" at the code level, but it feels like not a good use of my time to go into those weeds.

When I look at the code it seems well structured due to screaming architecture, and module based design.

At this point I haven't looked at code for many months. Before that, I spent 4 years hand coding a Google Docs competitor in JS without any libraries.

My brain feels equally as exercised (in fact more so as I am not as good at agentic coding as I was at real coding)

But now I'm making highly polished Mac OS apps and I really like that move from JS.

I feel... conflicted.

How many pixels wide is the hit zone?

Ah. My bad. I didn't review them I was just paying more attention to the op asking for a list of open source ones.

I'm seeing a lot right here: https://github.com/FluidInference/FluidAudio

Nice tip on FluidAudio that's the kind of thing I've been looking for. Thanks!

Classic HN. Thanks for keeping it real.

I do not want to game the system, I hate the idea of gaming the system. I just want to be nice, and I think that is precisely the reason why I'm not very rich.

Next time you build a large build try asking the LLM to make it as an AFK build and tell it that you need it to do everything in it's power to complete the build without your intervention. It's going to need a few tiers of tests from unit to smoke and screen tests. Now, I'm not saying this is easy to do. It requires an insane amount of up front thinking BUT if you (for the heck of it) want to make an overnight build this is one way.

FWIW While I have had created and run this kind of build a few times... I did not like the results! In the end, I personally like to be in the loop to test and feel how stuff is turning out as it goes.

Generally speaking if a company can game the system they will game the system.

Just talking about longer deep thought loops. You can do a LOT of deep thought at 15k a second and it still feels super fast.

Side note: I really believe in this technology if anyone building this happens to be reading this and is looking for help give me a shout.

They will come with corrective SSD and Ram that will enable stale models to get some amount of self correction. Then after that it will be a typical upgrade path. Actually a nice business model with upgrades built in.

If they supply something like an external hard drive formfactor with small ssd for a small corrective memory it could do very will IMHO

Yes but we're talking about the fullness of time as things play out. Much improvements will be made to OS models via distillation and then you also get 15k sec to make it think better.