HN user
jv AT vip.ie
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...
Yeah, I have been thinking exactly the same. Makes all the sense in the world and is inevitable as far as I can see.
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.
Why is no one talking about open source models being burned direct to chip and running inference at 10k-15k a second?
OS models close the gap (via distillation) with frontier models, then get burned to chip, then offer commoditized inference via data farms or local plugins.
With thought loops this fast even if the models are less smart they can be self correcting to level them selves up.
How does modo help vs using a skill or claud.md that says to always do this?
Not a critique just giving you a chance to sell it :)
I feel bad saying this because so many folks have not had the best of luck, but it's changed the game for me.
I'm building out large multi-repo features in a 60 repo microservice system for my day job. The AI is very good at exploring all the repos and creating plans that cut across them to build the new feature or service. I've built out legacy features and also completely new web systems, and also done refactoring. Most things I make involve 6-8 repos. Everything goes through code review and QA. Code being created is not slop. High quality code and passes reviews as such. Any pushback I get goes back in to the docs and next time round those mistakes aren't made.
I did a demo of how I work in AI to the dev team at Math Academy who were complete skeptics before the call 2 hours later they were converts.
One thing you could look into is body doubling sites like flow club. It doesn't solve the core issue but might help in a small way outside of work hours. Outside of the internet I keep hearing that Pickleball is the most social sport around! Also have you tried hanging out and working at Starbucks (or similar) after some time (weeks) in the same place it's inevitable to start making connections. Also co-working spaces can offer connections, and they usually have various club goings on on notes on the pin boards etc. One thing I do know is that it takes quite a few times / weeks of time turning up to the same place for conversation to start. Hope this is helpful in some way.
Hmm. TIL: The real exposure isn't Anthropic, OpenIA claiming your code, it's you unknowingly distributing someone else's GPL code because the model silently reproduced it, with essentially zero recourse for the model owner.
Any idiot can now prompt their way to the same software.
It may look the same, but it isn't the same.
In fact if you took the time to truly learn how to do pure agentic coding (not vibe coding) you would realize as a principal engineer you have an advantage over engineers with less experience.
The more war stories, the more generalist experience, the more you can help shape the llm to make really good code and while retaining control of every line.
This is an unprecedented opportunity for experienced devs to use their hard won experience to level themselves up to the equivalence of a full team of google devs.
Thanks, I've been very focused on lightwave and as a result let that one slide a bit. I'll try to get it working in next week or so.
Yes, since I spent over 10 years writing it in the first place it was easy to verify!
I used Claude to document, in great detail, a 500k-line codebase in about an hour of well-directed prompts. Just fully explained it, how it all worked, how to get started working on it locally, the nuance of the old code, pathways, deployments using salt-stack to AWS, etc.
I don't think the moat of "future developers won't understand the codebase" exists anymore.
This works well for devs who write their codebase using React, etc., and also the ones rolling their own JavaScript (of which I personally prefer).