Recent submissions

Comment · 1 month ago
if they do not release any model to the public: how would they make money then?

Their entire funding model depends on that they generate much revenue _soon_

Comment · 2 months ago
missing aqua voice's avalon 1.5 model there.
Comment · 5 months ago
Comment · 6 months ago
for me at least, yes. just wrote it to coworkers this afternoon. Behaves way more "stable" in terms of quality and i don't have the feeling of the model getting way worse after 100k tokens of context or so.

What i notice: after 300k there's some slight quality drop, but i just make sure to compact before that threshold.

Comment · 8 months ago
To be honest, but I would love to have some ecosystem around building apps which lets me share my custom apps with team members in my organization. Without having to take care of updating, provisioning, and distributing the app, etc.

even better if the apps are not electron bloated and mac-native.

Comment · 8 months ago
Really nice! I really enjoy it. The only thing I notice is when I'm using Claude code via SSH, the app hangs itself up once the conversation gets longer.

Termius, for example, doesn't have the problem.

Comment · 1 year ago
It seems like it works again.
Comment · 1 year ago
yes, getting the 529 http error code aka `overloaded`.
Comment · 1 year ago
you were involved with clear? damn! i was one of the first users back then, even using it to this day! monodraw looks awesome, will definitely check it out!
Comment · 1 year ago
using zen since about 7 months for all of my daily work + on my personal computer. the issues the comments describe here, never had those. it "just" works for me. donated to the project, i hope they go a long way.
Comment · 1 year ago
you can do using vimium :)
Comment · 2 years ago
Comment · 2 years ago
i'm interested as well.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton