tracyhenry
Joined 6 years ago
Karma
1,901
Submissions
306
Member since
Aug 29
Recent submissions
Comment · 1 month ago
I always think the best company to own an alway-on agent should be Apple, who owns the platform and is more privacy-focused. I hope they catch up and eventually eliminate others.
Comment · 1 month ago
This, like the hype of Jev on Twitter, totally ignores accuracy and generality across domains.
In my experience even structured LLM output performs poorly on classifier tasks. LLMs are trained to talk and think longer. If you don't give LLM enough space to reason it would become very dumb.
I'm not saying that Jev is way better, but that people way overindexed cost and speed.
Comment · 1 month ago
When the blog title is "world's first model for Generative UI", you are supposed to show something that GPT/Claude couldn't do. Instead it's all benchmark.
I don't know what media you are talking about. It's all slop worse than current slop.
Comment · 1 month ago
design is the hard problem. i don't know what hard problem this is trying to solve here
Comment · 1 month ago
Generative UI is unsolved because current models do not have taste and end up generating the same kind of slop.
I'm amazed that this blog doesn't even have a single screenshot/photo of the kind of UI they can generate.
Focusing on benchmarks in this domain feels very wrong.
Comment · 1 month ago
No one on HN seems to care about its crazy ability in 3D modeling?
3D might have just been solved like coding
Comment · 4 months ago
The only times I found the memory feature useful are in "projects" I created myself.
In a project my questions are usually revolved around the same topic. Having context carried across threads actually make a lot of sense.
In the general mode where I'm expecting models to be *stateless*, having memory is very annoying.
Comment · 4 months ago
At the end of the day, it only makes sense if watching a movie on AVP gives you immense joy, which is the case for me.
If you can charge your phone, you can charge your vision pro. The battery itself can last any movie with no problem.
Comment · 4 months ago
Not regularly, but I do watch movies on it once in a while (in those beautiful environments), especially when I'm on a flight.
WWDC also just rolled out some quite exciting features to RealityKit: https://developer.apple.com/videos/play/wwdc2026/279/ as well as visionOS itself (https://developer.apple.com/videos/play/wwdc2026/287/)
It makes me wonder if Apple is really giving it up as news have claimed.
Comment · 6 months ago
After all these, I still feel their voice AI interrupts quite a lot, especially when I pause just for 0.5 sec. Interestingly, when I tell it to interrupt less, it seems to be better.
Comment · 6 months ago
off topic but I just wonder if this page is AI-designed. It looks quite good to my eyes. I feel like prior to coding agents this would instead be a blog post with some charts.
Comment · 6 months ago
I'm building Eima (https://eima.app) which combines your Todo List and Calendar, allowing you to schedule your todos by simply dragging them onto the calendar.
Similar apps have existed before (like Amie), but they were nearly all VC-backed and had pretty much all pivoted to AI (e.g. being an AI note taker). Their approaches to a Todo-focused calendar has been largely unsatisfying due to the focus on Enterprise users and whatever is trendy.
Eima, in contrast, focuses on personal use and does one thing very well: scheduling your todos. In particular, I spent a lot of time making sure multi-occurrence todos work smoothly (e.g. todos that need multiple attempts or simply recurring todos). These were not addressed by prior tools at all and had been my biggest motivation to build Eima.
Would love some test users! If you end up wanting to give Eima a try please use the code EARLYEIMA to get it for free.
Applying ML, UX and Big Data tech to solve important & fun problems. MIT CSAIL alumni.
Top color: FFD700