Hacker Newsnew | past | comments | ask | show | jobs | submit | fassssst's commentslogin

Umm, what happened to zero trust? Network security is not sufficient.

Sure but I use Ableton, Lightroom, and Battlefield 6 daily.

It’s a bit low effort. If you like this kind of thing I’d suggest

https://roland50.studio/


Yes I agree, it is currently a side-project that is 2 days old! Also brilliant suggestion, played with it and really liked it!

DIY culture I guess, but yea both Claude and Codex have native phone apps that run the agent on a cloud VM and can push PRs.

Thieves will just ask their favorite chat bot to change the background of the photo.

Remove background from an image. Summarize some text. OCR to select text or click links in a screenshot. Relighting and centering you in your webcam. Semantic search for images and files.

A lot of that is in the first party Mac and Windows apps.


Selecting text in a photo is a game changer. I love it.

Wasn’t built in OCR an amazing feature?

We probably could have done it years earlier. But when it showed up… wow.


Post training :)


Latest iOS Safari: the viewport jumps around on all those demos. Really hurts your case.


iOS Safara user here. The viewport jumped for me only on the active search demo and only the first time when the result content was initially loaded. This can be easily fixed by having a fixed-size results box loaded from the beginning.


my htmx apps have 0 cls. You just have to care enough to do something about it.


Just like how people forgot how to patch phone lines and punch cards.


Either way it is text instructions used to call a function (via a JSON object for MCP or a shell command for scripts). What works better depends on how the model you’re using was post trained and where in the prompt that info gets injected.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: