Hacker News: sadfgknerknksdf

New comment by sadfgknerknksdf in "We found a division by zero bug in FFmpeg with a vibecoded fuzzer"

sadfgknerknksdf — Fri, 28 Aug 2026 00:22:14 +0000

If finding the bugs with LLMs is easy. Then making sure it doesn't break something else is just LLMs finding no bugs. Easy.

New comment by sadfgknerknksdf in "Maximizing the value of your Claude Code sessions"

sadfgknerknksdf — Fri, 14 Aug 2026 19:09:45 +0000

You can make your own status line with something like "120K/200K Fable 5", it's nice.

New comment by sadfgknerknksdf in "What's the deal with all the random weekly quota resets for agents lately?"

sadfgknerknksdf — Sun, 19 Jul 2026 08:03:57 +0000

It's a weird thing to optimize for. If you care about availability for work you can just pay more where it feels limitless and never look at the limits. I think a lot of people have a tendency to want to minmax as a "game". I also occasionally have the urge to do it but then realize it's a means to an end, not the end itself. I would feel good having maximised usage even if it wasn't productive usage which is irrational.

I think the main problem is the usage limits. You would never feel like you are saving money by watching movies on Netflix. If they didn't have limits, many might find themselves using agents less actually.