Viewing profile — kimi

I'm sure it was posted previously, but it's always nice to read. The first post seems to be from 16 years ago: https://news.ycombinator.com/item?id=1372371

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, …

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

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

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

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 str…

Archive returns 503 ATM....

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.…

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 …

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

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…

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…

Wish I had something like that when I was coding demos around 1988... :-) (Edit): you kids have it easy.

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

[dead]

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

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

...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 s…

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 th…

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

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

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 …