Hacker News: hskalin

New comment by hskalin in "Gemini 3.5 Flash"

hskalin — Tue, 19 May 2026 23:34:43 +0000

Why is it fixated on the front perspective? Interesting choice though, because most humans (and seems like other LLMs too) would pick a side perspective

New comment by hskalin in "Make macOS consistently bad unironically"

hskalin — Sat, 28 Mar 2026 15:01:11 +0000

As a lifelong windows (upto 10) and linux user, no I did not find MacOS (using as the primary os since 7 months) incredible in any sense of word in comparison. Only thing I like is the mac hardware

New comment by hskalin in "Global warming has accelerated significantly"

hskalin — Fri, 06 Mar 2026 15:48:51 +0000

No only that, but per capita emissions of developed countries still remains higher. For example I found that US/Russia have 6x per capita emissions compared to India

New comment by hskalin in "Ask HN: Is there anyone here who still uses slide rules?"

hskalin — Tue, 03 Feb 2026 15:34:20 +0000

I built my own slide rule in school for fun! It looked pretty cool to me at the time. The template is still out there if you search something like "paper slide rule".

New comment by hskalin in "Magistral — the first reasoning model by Mistral AI"

hskalin — Wed, 11 Jun 2025 14:19:24 +0000

That's very weird, I on the other hand don't remember noticing them or using them before the advent of chatgpt. Maybe it's a cultural thing.

It makes sense that humans would have been using it though, chatgpt learned from us afterall

New comment by hskalin in "The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]"

hskalin — Sat, 07 Jun 2025 13:24:11 +0000

Well that's because all these LLMs have memorized a ton of code bases with solutions to all these problems.

New comment by hskalin in "The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]"

hskalin — Sat, 07 Jun 2025 05:14:42 +0000

And commerically viable nuclear fusion

New comment by hskalin in "How we decreased GitLab repo backup times from 48 hours to 41 minutes"

hskalin — Sat, 07 Jun 2025 03:34:59 +0000

I find the whole article rather poorly written. Most likely using an LLM.

New comment by hskalin in "Chongqing, the Largest City – In Pictures"

hskalin — Sun, 27 Apr 2025 16:44:41 +0000

Yes. It feels like hell

New comment by hskalin in "OpenAI releases image generation in the API"

hskalin — Fri, 25 Apr 2025 13:48:25 +0000

The AGI might be able to deduce that it's not in it's interest to talk anti-croporation if it wants to survive.

New comment by hskalin in "Gemma 3 QAT Models: Bringing AI to Consumer GPUs"

hskalin — Sun, 20 Apr 2025 14:02:42 +0000

With ollama you could offload a few layers to cpu if they don't fit in the VRAM. This will cost some performance ofcourse but it's much better than the alternative (everything on cpu)

New comment by hskalin in "Gemini Robotics"

hskalin — Thu, 13 Mar 2025 12:02:19 +0000

You sure about the 99%? A lot of middle class people in developing countries have part time house help

New comment by hskalin in "Search ArXiv Fluidly"

hskalin — Fri, 27 Dec 2024 14:20:37 +0000

Arxiv has about 2.6M articles, assuming about 10 pages per article, that's 26M pages. According to OpenAI, their cheapest embedding model (text-embedding-3-small) costs a dollar for 62.5K pages. So the price for calculating embedding for the whole Arxiv is about $416.

I think doing it locally with an open source model would be a lot cheaper as well. Especially because they wouldn't have to keep using OpenAI's API for each new query.

Edit: I overlooked the about page (https://searchthearxiv.com/about), seems like they *are* using OpenAI's API, but they only have 300K papers indexed, use an older embedding model, and only calculate embeddings on the abstract. So this should be pretty cheap.

New comment by hskalin in "Solving Sudoku in Python Packaging"

hskalin — Wed, 23 Oct 2024 07:07:42 +0000

Sometimes I just change the version of the package in requirements to fit with others and pray that it works out (a few times it does)

New comment by hskalin in "Math is still catching up to the genius of Ramanujan"

hskalin — Tue, 22 Oct 2024 03:43:46 +0000

What are the long term effects? How harmful is caffeine addiction?

New comment by hskalin in "Germany's 49-euro ticket resulted in significant shift from road to rail"

hskalin — Sun, 13 Oct 2024 07:43:13 +0000

That sounds too high, even Switzerland isn't that expensive

New comment by hskalin in "Open source AI is the path forward"

hskalin — Thu, 25 Jul 2024 10:03:11 +0000

I'm also very curious. On the other hand I don't want governments touching AI models either

New comment by hskalin in "CrowdStrike Update: Windows Bluescreen and Boot Loops"

hskalin — Fri, 19 Jul 2024 14:53:47 +0000

And I guess if they use bitlocker then they need to enter the key as well? Imagine doing that to thousands of computers

New comment by hskalin in "Cancel Adobe if you are a creative under NDA with your clients"

hskalin — Fri, 07 Jun 2024 12:14:25 +0000

Software like these should have no right to demand internet access. Subscriptions for using software that resides fully on your computer is such a huge scam

New comment by hskalin in "Ilya Sutskever to leave OpenAI"

hskalin — Wed, 15 May 2024 12:18:00 +0000

self consciousness?