Hacker News: kimi

New comment by kimi in "Show HN: Contrapunk – Real-time counterpoint harmony from guitar input, in Rust"

kimi — Sun, 05 Apr 2026 08:16:00 +0000

I was bitten by the same issue. Maybe add a line to the docs.

New comment by kimi in "Model collapse is already happening"

kimi — Thu, 26 Mar 2026 05:23:57 +0000

Actually, both will, as they are not separate within the LLM. The thing is, one is a style issue, the other content. You can express original ideas and still use a lot of em dashes, or produce slop with a lot of typos in it.

New comment by kimi in "Model collapse is already happening"

kimi — Wed, 25 Mar 2026 19:23:54 +0000

I have a pet-peeve with this. As a non-native English speaker, I find it very useful to dictate multiple notes, in different languages, and have the LLM produce clear English prose out of it. The prose may be LLM-generated, but I edit it when needed to make sure that the contents is 100% mine.

It's like dictating to a typist like they did in the 60's - he will make sure that your letter looks professional and will fix your grammar, but you will sign the letter. This is totally different from LLM spam, the kind that inflates a sentence into a three-page article full of nothing.

So - is it a problem if the language reverts to a mean? that is the point of a shared language, right?

New comment by kimi in "A 6502 disassembler with a TUI: A modern take on Regenerator"

kimi — Tue, 24 Mar 2026 09:16:09 +0000

Wish I had something like that when I was coding demos around 1988... :-)

(Edit): you kids have it easy.

New comment by kimi in "What if Python was natively distributable?"

kimi — Thu, 19 Mar 2026 19:12:04 +0000

Answering the question: it would be called "the Erlang VM", and you'd use Elixir to program it.

https://elixir-lang.readthedocs.io/en/latest/mix_otp/10.html

New comment by kimi in "1M context is now generally available for Opus 4.6 and Sonnet 4.6"

kimi — Sat, 14 Mar 2026 06:49:30 +0000

How is that relevant? we are talking about models, now what you do with them.

QueueMetrics for Teams Helps You Spot Impersonation Scams Before They Strike

kimi — Mon, 02 Mar 2026 13:41:20 +0000

Article URL: https://www.queuemetrics.com/blog/2026/03/02/queuemetrics-protects-teams-impersonation/

Comments URL: https://news.ycombinator.com/item?id=47217844

Points: 3

# Comments: 0

New comment by kimi in "SynthID – A tool to watermark and identify content generated through AI"

kimi — Sat, 30 Aug 2025 14:48:55 +0000

For text, have a big model generate the "intelligent" answer, and then ask a local LLM to rephrase.

New comment by kimi in "Don't “let it crash”, let it heal"

kimi — Sun, 10 Aug 2025 07:13:29 +0000

...and does no harm for unfixable bugs. It's the logical equivalent of "switch off and on again" that as we know fixes most issues by itself, but happening only on a part of your software deployment, so most of it will keep running.

New comment by kimi in "AI overviews cause massive drop in search clicks"

kimi — Thu, 24 Jul 2025 07:13:15 +0000

I do the same thing - Instead of going first to an unknown site that might (will?) be ad-infested and possibly AI generated, so that a phrase becomes a 1000-word article, I read the comments on HN, decide if it's interesting enough to take the risk, and then click. If it's Medium or similar, I won't click.

Hey, coming out feels good - I thought I was the only one.

New comment by kimi in "Show HN: WTFfmpeg – Natural Language to FFmpeg Translator"

kimi — Wed, 23 Jul 2025 07:34:27 +0000

Instead of LLM, Python and whatnot, it could have been a cheatsheet: https://github.com/scottvr/wtffmpeg/blob/12767e7843b9fd481ba...

New comment by kimi in "Hugging Face just launched a $299 robot that could disrupt the robotics industry"

kimi — Wed, 09 Jul 2025 14:35:54 +0000

In the end, I'm not sure I get what this is for - the venturebeat piece seems written by an AI.

New comment by kimi in "XSLT – Native, zero-config build system for the Web"

kimi — Fri, 27 Jun 2025 09:15:52 +0000

Just my two cents - the worst pieces of tech I ever worked with in my 40+ year career were Hibernate (second) and XSLT templating for an email templating system around 2005. Would not touch it with a stick if I can avoid it.

New comment by kimi in "32 bits that changed microprocessor design"

kimi — Fri, 23 May 2025 12:24:35 +0000

I don't think it was single-cycle, someone mentions a STRCPY instruction that would be quite hard to do single-cycle....

Going to the cloud' could also mean locking into a forever sub-contractor

kimi — Mon, 19 May 2025 12:53:57 +0000

Article URL: https://berthub.eu/articles/posts/beware-cloud-is-part-of-the-software/

Comments URL: https://news.ycombinator.com/item?id=44029348

Points: 5

# Comments: 0

New comment by kimi in "The Beam"

kimi — Tue, 13 May 2025 08:34:19 +0000

Like Java?

New comment by kimi in "Nevermind, an album on major chords"

kimi — Sun, 04 May 2025 16:40:37 +0000

Don't forget Ramones.

New comment by kimi in "Get your Minitel back, the COMPUTEL videotex BBS is back"

kimi — Thu, 24 Apr 2025 08:10:58 +0000

Related: Retrocampus BBS is a dial-up BBS you can call with your Videotel terminal in Italy... or access with your browser right now - https://bbs.retrocampus.com/

Of course I'm not suggesting at all that you waste an otherwise perfectly productive day playing Zork I-II-III or Hitchhiker's on it... ;-)

New comment by kimi in "Unauthenticated Remote Code Execution in Erlang/OTP SSH"

kimi — Thu, 17 Apr 2025 15:02:29 +0000

Yes - one of the many things that you can find in OTP is a programmable SSH/SCP client and server. The vulnerability is in the server component.

See for example https://blog.differentpla.net/blog/2022/11/01/erlang-ssh/

Unauthenticated Remote Code Execution in Erlang/OTP SSH

kimi — Thu, 17 Apr 2025 13:29:44 +0000

Article URL: https://nvd.nist.gov/vuln/detail/CVE-2025-32433

Comments URL: https://news.ycombinator.com/item?id=43716526

Points: 199

# Comments: 51