jerryliu12

Joined 7 years ago

Karma
151
Submissions
26
Member since
Oct 17
feel free to email me at liu.z.jerry on gmail
View on Hacker News

Recent submissions

Comment · 4 months ago
Personally feel like it could be more ambitious with what it creates.
Comment · 1 year ago
Woah didn't know about VNRecognizeTextRequest, that's super cool thanks for flagging!
Comment · 1 year ago
Looks awesome, but a 30B model is too big. Vast majority of people probably have 32GB of RAM or less unfortunately.
Comment · 1 year ago
Yep, you figured out how it works! That was the easiest solution I could come up with. I'm sure theres additional context on other screens but this was a good 90/10 solution.
Comment · 1 year ago
Thanks, yeah I do need to flesh out the debugging options. In the menu bar you can click the Dayflow icon which should allow you to view the recordings folder. The sqlite db is in that folder too if you want to poke around there as well.
Comment · 1 year ago
Thanks! Wanted to build something I'd personally be comfortable using.
Comment · 1 year ago
Gemini 2.5 Pro is pretty expensive, mostly because videos take up a lot of tokens. It's roughly 1 million input tokens/hr, with a relatively insignificant amount of output tokens. Fortunately, Gemini has a very generous free tier, which is more than enough to cover daily usage. If you set up one paid project (and just don't consume any tokens), you can still use the free tier on a different project, and they can't train on your data.
Comment · 1 year ago
If I had to put a grade on my own experience and evals, Gemini 2.5 pro produces A- results and qwen2.5vl is maybe like B-/C+. Obviously everything's nondetermistic, so it's hard to guarantee a level of quality.

I'm reading through papers that suggest it should be possible to get SOTA performance on local models via distillation, and that's what I'll experiment with next.

Comment · 1 year ago
You definitely could! I think it would just be harder to get good semantic understanding of what you did during a segment of time without LLMs.
Comment · 1 year ago
Yea, honestly I would hate if people used this to track _other_ people, especially bosses. I wanted to build something that gave people more agency to do more with their precious time, but there definitely is a fine line here.
Comment · 1 year ago
Yep, helping people understand their distraction patterns would be an amazing feature. I find myself doing the same thing, funnily enough I also have that same Youtube extension.
Comment · 1 year ago
Wow, yeah that's clever I hadn't thought of that. Will add as an advanced setting.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton