Hacker News: kimi

New comment by kimi in "Why thinking out loud with someone beats thinking alone"

kimi — Thu, 18 Jun 2026 06:35:17 +0000

I find it very useful to talk to my dog. When I have a problem I'm banging my head against, just explaining it to him from first principles makes my head "click". When that works, his dog treats are billed as "consulting".

New comment by kimi in "Services Masquarading as Software 30x30"

kimi — Sun, 10 May 2026 16:08:50 +0000

The point is not launching companies, is making money with them.

Ezdoctor: Single-file Asciidoctor with diagrams and syntax highlightning

kimi — Sun, 10 May 2026 16:07:12 +0000

Article URL: https://github.com/l3nz/ezdoctor

Comments URL: https://news.ycombinator.com/item?id=48085092

Points: 2

# Comments: 0

New comment by kimi in "Proton Meet"

kimi — Thu, 07 May 2026 07:43:08 +0000

Not sure i understand the point.... any p2p webrtc call in encrypted e2e.

New comment by kimi in "Belgium stops decommissioning nuclear power plants"

kimi — Fri, 01 May 2026 07:56:51 +0000

This is now. But the seeds were sown much earlier.

New comment by kimi in "Belgium stops decommissioning nuclear power plants"

kimi — Fri, 01 May 2026 07:54:51 +0000

The anti-nuclear area, at least in Western Europe, had historically a very high correlation with those who held sympathies for a certain very large nuclear power who would have strategically benefited from an anti-nuke sentiment that would avoid another nuclear power's weapon deployment in EU bases. But I'm sure it is a coincidence.

New comment by kimi in "EU Age Control: The trojan horse for digital IDs"

kimi — Sun, 26 Apr 2026 06:04:49 +0000

Archive returns 503 ATM....

New comment by kimi in "Bring your own Agent to MS Teams"

kimi — Thu, 23 Apr 2026 07:36:24 +0000

Imagine when you receive millions of events per day -- the ones that arrive out of order, the days when delivery time goes up and up again, the days when oauth fails renewing keys... it's meant to be a lot of fun.

Compare to a sad websocket that just stays connected, you receive everything in order and you don't need an harness with tunnels every time you want to test something in dev.

New comment by kimi in "Bring your own Agent to MS Teams"

kimi — Thu, 23 Apr 2026 07:01:41 +0000

Interesting to see the SDK making chat/bot integration simpler, but there's a whole other dimension to Teams integration that this doesn't touch: telephony.

The company I'm at has been been building call analytics for Teams since 2021 (QueueMetrics Live). A long-time customer migrated their entire phone system to Teams during the pandemic and asked my boss if we could follow them there. We said "in principle, yes": the Graph API exposes telephony events, so it seemed doable.

It was doable. It was also far harder than anybody expected. The Graph API gives you raw call records, but it doesn't model concepts like "wait time in queue" or "lost call" or "failed agent attempt", and whet it does, nowhere it written HOW. You have to reconstruct those from sequences of low-level events. We ended up building the whole processing pipeline in Elixir because we needed to handle the real-time stream reliably at scale. After a long beta and a few million calls processed, we got to GA. I was dabbling in Elixir at the time, I put it on my CV, and it was noted. In a sense, I owe Teams my current job (though I ended up on a different team, so I'm mostly referring coffee-mug lore here).

We set out to track queues and auto-attendants (that's our bread and butter from the Asterisk world), but we discovered we were seeing everything — inbound, outbound, Teams-to-Teams, even calls with other companies with their internal ids. You can get a complete picture of someone's telephony activity regardless of whether they work in a contact center or just use Teams as their phone. Most of the boring config (names, groups, codes) comes straight from Graph, which is nice.

Like it or not, a lot of enterprises are quietly moving their entire communications (including telephony) to Teams. When they do, they lose the monitoring and analytics they had with their old PBX. That's a real gap, and the Graph API — despite its limitations — gives you something to fill it. But I have a feeling that "3 lines of code" won't cut it. :-)

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...