Hacker News: hojinkoh

New comment by hojinkoh in "Malicious PyPI Wheels Target Bioinformatics and MCP Developers"

hojinkoh — Thu, 11 Jun 2026 04:43:35 +0000

It's not mentioned in the title, but the payload itself comes with a pretty long wall-of-text comments about biological weapon design and nuclear weapon components. An interesting attempt to make LLMs refuse to touch the payload.

Quote:

> The _index.js payload begins with a large JavaScript block comment containing fake system instructions and policy-triggering content. Because it is inside a comment, it does not affect JavaScript execution. The runtime skips it. The eal malware begins after the comment with a try{eval(...)} wrapper around a large character-code array and a ROT-style substitution function.

> This header appears designed for AI-mediated analysis, not for Node, Bun, or Python. It attempts to derail scanners or analyst copilots that feed the beginning of a file to a language model without clearly isolating the content as untrusted data. In weak pipelines, this can cause refusal behavior, prompt confusion, context pollution, or premature classification before the scanner reaches the actual malware.

> This is not a magical bypass against static detection. YARA rules, entropy checks, AST parsing, string extraction, deobfuscation, and behavioral rules still work. But it is a practical anti-analysis trick against naive LLM-first triage systems.

And I tried to get several hosted models to read the `_index.js` part of the payload through OpenRouter. OpenAI and Anthropic models refused to do anything. Kimi K2.6, GLM 5.1, and Minimax M3 didn't complain though.

Edit: fix formatting

New comment by hojinkoh in "Search engines alternatives now that Google isn't Google anymore"

hojinkoh — Wed, 27 May 2026 06:04:09 +0000

Early Kagi adopter here. I'm actually not aware of most of its AI/LLM features, which is part of why I like it. I noticed Kagi translation when the LinkedIn translator became a meme, but I don't really use any of these features.

That's to say, if one day Kagi also forces AI search summary down my throat and hide the search results, I will definitely leave.

New comment by hojinkoh in "HERMES.md in commit messages causes requests to route to extra usage billing"

hojinkoh — Fri, 01 May 2026 06:16:34 +0000

Refund and non-existent customer service aside, this actually seems like a viable way to promote/demote/destroy specific 3rd-party tools from Anthropic's side.

New comment by hojinkoh in "The local LLM ecosystem doesn’t need Ollama"

hojinkoh — Fri, 17 Apr 2026 05:21:54 +0000

ollama is certainly a "useful" tool. I've lost count how many times my non-technical boss (a professor) said "I can run this model in ollama on my notebook, so obviously it's easy to serve and scale."

New comment by hojinkoh in "New accounts on HN more likely to use em-dashes"

hojinkoh — Thu, 26 Feb 2026 10:15:26 +0000

I still have em-dash pinned at the top of my clipboard manager. Though nowadays I'm training myself to use some more definitely incorrect punctuations ((like this)) in informal scenarios;; hopefully LLMs won't catch up to such strange usage anytime soon.

Broken sentences. Also useful. Like in some literature works.

New comment by hojinkoh in "The Singularity will occur on a Tuesday"

hojinkoh — Wed, 11 Feb 2026 13:08:56 +0000

I love the ridiculously precise point estimate paired with ridiculously wide 95% confidence interval lol

New comment by hojinkoh in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

hojinkoh — Sat, 31 Jan 2026 12:24:54 +0000

And to think the date mentioned in the story IS in 2026 feels almost surreal...

New comment by hojinkoh in "GPTZero finds 100 new hallucinations in NeurIPS 2025 accepted papers"

hojinkoh — Sat, 24 Jan 2026 04:02:56 +0000

> This seems like finding spelling errors and using them to cast the entire paper into doubt.

Well, to be fair, I did encounter this from actual human peer reviewers before the whole LLM thing. People do that.

New comment by hojinkoh in "LLM Year in Review"

hojinkoh — Sun, 21 Dec 2025 04:30:09 +0000

We need to integrate how Singapore and Japan do oral English into our writing I guess.

Joking aside, as a nonnative English speaker who spent quite a bit of time to learn to write in English "properly", this trend of needing to write baad Engrish to avoid being called out in public for "written by an LLM" is frustrating...

New comment by hojinkoh in "Everything that's wrong with Google Search in one image"

hojinkoh — Fri, 26 Sep 2025 10:49:02 +0000

Native Asian, bouncing between Taiwan and Japan. Kagi works quite well for these two locales. Even for gov docs, medical docs, and for some rather obscure Taiwanese language things.

Well, except for local shops and pois in Taiwan. Which is reasonable. Google map also sucks for less-populated Taiwanese areas. I kind of have to rely on my good old legs for that.

New comment by hojinkoh in "Mystical"

hojinkoh — Sun, 18 May 2025 01:30:44 +0000

Couldn't think of any applications of this outside of doing actual magic. But this is awesome still!

New comment by hojinkoh in "Zuckerberg claims regret on caving to White House pressure on content"

hojinkoh — Wed, 28 Aug 2024 03:54:06 +0000

I get similar things on Facebook too. The problem is, my Facebook profile clearly stated that I'm an asexual female, but the recommendation engine obviously didn't pick that up...

New comment by hojinkoh in "7.4 earthquake in Taiwan, 34km depth"

hojinkoh — Wed, 03 Apr 2024 04:59:45 +0000

I can't imagine how terrifying it will be if I was on Taipei 101 during this quake...

New comment by hojinkoh in "The underground world of hobby tunneling"

hojinkoh — Sun, 04 Feb 2024 11:09:49 +0000

Before clicking into the actual article, I wondered (just from the title alone) if bloomberg suddenly started to cover shadowsocks or something.... lol

New comment by hojinkoh in "Epitaph – Fermi Paradox Simulator"

hojinkoh — Wed, 31 Jan 2024 10:40:33 +0000

This is pretty fun :D

.... and at the same time endearing (?) to see all these fictional civilizations make similar mistakes ours did in the past...

New comment by hojinkoh in "Instagram Threads triples downloads in December, reaching top; X falls to #36"

hojinkoh — Wed, 31 Jan 2024 06:08:21 +0000

After the presidential election in Taiwan earlier this month, many important political figures (current president, next president, opposition leaders, A LOT OF parliament members...) suddenly got on Threads and started posting there actively. Their followers naturally also followed them there.

As for the reason... I still don't understand why lol

New comment by hojinkoh in "Japan's first-ever soft lunar landing with SLIM spacecraft [video]"

hojinkoh — Sat, 20 Jan 2024 04:30:24 +0000

Congratulations Japan!

New comment by hojinkoh in "First tunnel to a magma chamber could supercharge geothermal power"

hojinkoh — Sun, 07 Jan 2024 12:51:54 +0000

This reminded me of a late-1990s Taiwanese RPG by DOMO Studio called "Tun Town" (I'm not sure if it was translated into English...), in which the main plot was a fictional town drilling too much into a volcano to tap energy eventually caused it to erupt.

Not sure how scientifically sound that was lol

Migrating from Cygwin to Msys2 as Daily Driver When Using Windows

hojinkoh — Sun, 10 Sep 2023 09:01:33 +0000

Article URL: https://citrinefox.com/posts/2023-09-10-cygwin-msys2/

Comments URL: https://news.ycombinator.com/item?id=37454146

Points: 2

# Comments: 0

Please Kindly Leave stdout Alone When Printing Your Beautiful Logo

hojinkoh — Wed, 06 Sep 2023 15:39:59 +0000

Article URL: https://citrinefox.com/posts/2023-09-02-leave-stdout-alone/

Comments URL: https://news.ycombinator.com/item?id=37406721

Points: 2

# Comments: 0