Preferences

44za12
Joined 165 karma

  1. Love the minimalism.
  2. Shameless plug.

    I’ve been using a cli tool i had created for over 2 years now, it just works. I had more ideas but never got to incorporate those.

    https://github.com/44za12/horcrux

  3. Have been using remove.bg for this for years now.
  4. Like a sempahore?
  5. I’ve had great luck with all gemma 3 variants, on certain tasks it the 27B quantized version has worked as well as 2.5 flash. Can’t wait to get my hands dirty with this one.
  6. Can you benchmark Kimi K2 and GLM 4.5 as well? Would be interesting to see where they land.
  7. That was quick, vibe coded, I presume?
  8. The ability to submit a story using a curl would have been fun.
  9. Tried that it’s taking exactly as much time as my program.
  10. I have breach parser that i had written to parse through over 3 billion rows of compressed data (by parsing i simply mean searching for a particular substring), I’ve tried multiple LLMs to make it faster (currently it does so in <45 seconds on an M3 pro mac) none have been able to do that yet.

    https://github.com/44za12/breach-parse-rs

    Feel free to drop ideas if any.

  11. Why not use something like litellm?
  12. Making a model better than proprietary models is in fact making a model better than their closed source models if you believe the benchmarks.
  13. With claude code and Kilo as well. I’m using moonshot’s API.
  14. I am on the pro plan, I was considering Max, but then i found kimi and I’m getting used to it.
  15. I pay for Cursor, OpenAI and kimi (to use with Claude Code), OpenAI is good with quickly refining my thoughts, Cursor’s subscription I’m reconsidering to cancel bought it for Claude but the rate limits are making it impossible for me to find it useful. Kimi is what truly surprises me, Claude code shows this conversation costed you $500 (based on Opus usage which is mapped to kimi k2) while I’ve barely spent $2. I have Ollama as well, majorly to quickly test small models that could be improved for our usecase through finetuning.
  16. Is it something like tree of thought reasoning?
  17. I don’t get the hype with OpenAI OSS, they would never make a model better than their proprietary models open source, and the other open source models beat GPT and family so why the wait?
  18. “I used all the top tier ‘Open Source LLMs’ and they suck I was right, like always, LLMs suck so hard, my job is safe!”
  19. Honestly, the fact that “scan everyone’s encrypted messages” keeps coming back like a bad sequel says a lot about how governments see privacy, as a speed bump, not a right. Every time this proposal pops up, it’s wrapped in “think of the children” language, but the end result is always the same: less security for everyone, more power for people who already have too much. At some point, you have to wonder if the real goal is to make everyone so paranoid they just stop communicating altogether. Here’s hoping enough people still care to push back—otherwise, we’ll all be talking in code again, and not the fun kind.
  20. Alright, plugged it to claude code ready for some tests, forget claude if it’s better than even Kimi, it’s going to be my go to.
  21. Every time someone calls a product “dumb,” I get a little excited, because it usually means it’s actually smart. The internet is drowning in “smart” stuff that mostly just spies on you and tries to sell you socks. Sometimes, I just want a pipe that does what it says on the tin; move my bits, shut up, and don’t ask for my mother’s maiden name.
  22. You know what’s wild? We’ve reached a point where the “download our app!” pop-up is basically the digital equivalent of a mall kiosk worker chasing you down with a lotion sample. I just want to read the article, not sign up for a recurring relationship. The web is supposed to be open, frictionless, and—dare I say—fun. Instead, it’s become a minefield of dark patterns, nag screens, and “please enable notifications!” popups.

    I love that this post is pushing back on the norm. Maybe, just maybe, we can start a movement to make the web usable again. Or at least make “No, thanks” actually mean “No, thanks.”

  23. What models are supported, can we add custom models? I’m struggling to add Kimi K2 to cursor and surf.
  24. Would 100% recommend, cheapest bare metal you can get, AFAIK.
  25. I absoltuley love it. Recently used this to host my blog along with multiple hobby projects on my 5-6 years old Raspberry Pi, more on it here:

    https://aazar.me/posts/reincarnating-a-raspberry-pi

  26. Oh, the irony. Just checked on mobile data, VPN etc. Seem to be working.
  27. This is super exciting! The “Cloudflare Tunnel” lock-in has always bugged me, so seeing an open source option is genuinely refreshing. I’m especially curious how Pangolin handles the gritty stuff—flaky networks, authentication headaches, scaling up when things get real. If anyone’s kicked the tires on this in the wild, how does it compare to the “it just works” magic of Cloudflare? Bonus points if you’ve wrangled it into playing nice with self-hosted stuff on a home connection. For context, I’ve got a Raspberry Pi running my blog and a bunch of other hobby projects from home, so real-world stories would be gold.
  28. I’ve been looking for a better ecosystem than Apple. This looks like it.

This user hasn’t submitted anything.

Keyboard Shortcuts

Story Lists

j
Next story
k
Previous story
Shift+j
Last story
Shift+k
First story
o Enter
Go to story URL
c
Go to comments
u
Go to author

Navigation

Shift+t
Go to top stories
Shift+n
Go to new stories
Shift+b
Go to best stories
Shift+a
Go to Ask HN
Shift+s
Go to Show HN

Miscellaneous

?
Show this modal