Hacker News: curioussquirrel

New comment by curioussquirrel in "Google releases Gemma 4 open models"

curioussquirrel — Sat, 04 Apr 2026 07:31:24 +0000

Give Gemma 31B a shot for translation, it does a very good job at that given its size.

New comment by curioussquirrel in "Google releases Gemma 4 open models"

curioussquirrel — Sat, 04 Apr 2026 07:27:48 +0000

We're doing multilingual testing and I can confirm what you've observed: Gemma 4 is surprisingly good at multilingual tasks, especially given its size. This is mostly true for the dense 31B model.

New comment by curioussquirrel in "Google releases Gemma 4 open models"

curioussquirrel — Sat, 04 Apr 2026 07:25:53 +0000

Same, I quickly tested it for code gen and it produced mostly good code for simple problems, but it sometimes hallucinated words in non-English scripts inside the code.

New comment by curioussquirrel in "Google releases Gemma 4 open models"

curioussquirrel — Sat, 04 Apr 2026 07:22:35 +0000

For anyone interested in multilingual performance, which is not usually well benchmarked or reported: Gemma 4 does really well, especially the dense 31B version. In fact, it outperforms many models with an order of magnitude higher number of parameters.

It is not quite capable of performing work on really long tail languages, but their claim of 35 languages supported (and a hint of some knowledge of up to 140) was substantiated by our tests.

If you're doing work outside of English and/or need to run a translation model in your terms, Gemma 4 is a very good candidate.

New comment by curioussquirrel in "Claude Code's source code has been leaked via a map file in their NPM registry"

curioussquirrel — Tue, 31 Mar 2026 18:24:04 +0000

Thank you. +1. There are obviously differences and things getting lost or slightly misaligned in the latent space, and these do cause degradation in reasoning quality, but the decline is very small in high resource languages.

psmux: Terminal multiplexer for Windows – tmux alternative

curioussquirrel — Sun, 18 Jan 2026 20:32:21 +0000

Article URL: https://github.com/marlocarlo/psmux

Comments URL: https://news.ycombinator.com/item?id=46671852

Points: 2

# Comments: 0

New comment by curioussquirrel in "enclose.horse"

curioussquirrel — Sat, 10 Jan 2026 12:41:21 +0000

Such a good game and execution. Thank you

Offline Regains Its Value

curioussquirrel — Tue, 06 Jan 2026 21:24:34 +0000

Article URL: https://blog.avas.space/real-life-value/

Comments URL: https://news.ycombinator.com/item?id=46519013

Points: 1

# Comments: 0

New comment by curioussquirrel in "OpenAI declares 'code red' as Google catches up in AI race"

curioussquirrel — Thu, 04 Dec 2025 14:04:45 +0000

And regarding specific models - we obviously only tested a few languages, and there are thousands of them in the world. But Gemini seems to lead the pack basically regardless of the language your throw at it. YMMV.

New comment by curioussquirrel in "OpenAI declares 'code red' as Google catches up in AI race"

curioussquirrel — Thu, 04 Dec 2025 14:03:39 +0000

In our previous tests, when it was 1.5 Pro against GPT 4o and Claude Sonnet 3.7, Gemini wasn't winning in the multilingual race, but it was definitely competitive. 2.5 and 3.0 seems to be big leaps from the 1.5 days. That said, it also depends on the testing methodology; we tested a bunch of use cases mostly to test core linguistic proficiency. Not as much complex tasks in language or cultural knowledge.

New comment by curioussquirrel in "OpenAI declares 'code red' as Google catches up in AI race"

curioussquirrel — Wed, 03 Dec 2025 07:10:21 +0000

This is probably not a core concern for most HN readers, but at work we do multilingual testing for synthetic text data generation and natural language processing. Emphasis on multilingual. Gemini has made some serious leaps from 1.5 to 2.5 and now 3.0, and is actually proficient in languages that other models can only dream of. On the other hand, GPT-5 has a really mixed performance in a lot of categories.

New comment by curioussquirrel in "OpenAI declares 'code red' as Google catches up in AI race"

curioussquirrel — Wed, 03 Dec 2025 07:04:12 +0000

You could ask GPT for what it knows about you and use it to seed your personal preferences to a new model/app. Not perfect and probably quite lossy, but likely much better than starting from scratch.

My data should not be your cookie jar

curioussquirrel — Sat, 29 Nov 2025 16:23:06 +0000

Article URL: https://blog.avas.space/cookie-jar/

Comments URL: https://news.ycombinator.com/item?id=46088706

Points: 3

# Comments: 0

New comment by curioussquirrel in "AniFlow – Yet another AI anime image generator"

curioussquirrel — Sat, 29 Nov 2025 06:30:01 +0000

Animation generator without a single demo/example animation on the page?

New comment by curioussquirrel in "We're losing our voice to LLMs"

curioussquirrel — Thu, 27 Nov 2025 22:59:55 +0000

+1 on this one! I only use LLMs once I'm done with writing, and basically using them as my editor.

In case it helps anyone, here is my prompt:

"You are a professional writer and editor with many years of experience. Your task is to provide writing feedback, point out issues and suggest corrections. You do not use flattery. You are matter of fact. You don't completely rewrite the text unless it is absolutely necessary - instead you try to retain the original voice and style. You focus on grammar, flow and naturalness. You are welcome to provide advice changing the content, but only do that in important cases.

If the text is longer, you provide your feedback in chunks by paragraph or other logical elements.

Do not provide false praise, be honest and feel free to point out any issues."

(Yes, you kind of need to repeat you're actively not looking for a pat on the back, otherwise it keeps telling you how brilliant your writing is instead of giving useful advice.)

New comment by curioussquirrel in "GitHub: Git operation failures"

curioussquirrel — Tue, 18 Nov 2025 21:16:39 +0000

Same, even started adding new ssh keys to no avail... (I was getting some nondescript user error first, then unhealthy upstream)

New comment by curioussquirrel in "Beets: The music geek’s media organizer"

curioussquirrel — Mon, 10 Nov 2025 11:01:25 +0000

A very similar workflow on my end, both beets as the main tagger/organizer and Picard to pick up whatever can't be processed through beets. Beets is amazing!

New comment by curioussquirrel in "Wharton AI 2025 Adoption Report"

curioussquirrel — Sun, 09 Nov 2025 17:02:18 +0000

Surprised this did not get any attention whatsoever. Some really surprising findings in it: 75% of firms already have a positive return on investment from AI, less than 5% negative return. Also 46% of businesses leaders now use AI daily themselves.

New comment by curioussquirrel in "Samsung Family Hub for 2025 Update Elevates the Smart Home Ecosystem"

curioussquirrel — Sun, 09 Nov 2025 16:51:04 +0000

Although I loathe ads, I think that for new products where the presence of ads is disclosed clearly upfront, this is acceptable. Especially if this comes with a discount. We have Kindles with and without ads and people are generally fine with it.

But the fact that this gets retrofitted to fridges that people already bought, without any way of opting out or other mitigation, is criminal. Is this a lawsuit in the making? Am I naive?

New comment by curioussquirrel in "You can't turn off Copilot in the web versions of Word, Excel, or PowerPoint"

curioussquirrel — Thu, 30 Oct 2025 22:26:33 +0000

Azure copilot is really something. It can't see the context of the page it's embedded in, and the message you send is limited to 500 characters, so good luck pasting a log or configuration.