Not to be confused with Kimi K2. Out of all the names they could've used, they picked one that would be confusing.
Not to be confused itself with K2 Think by MBZUAI...
K2 Horizon: A connected fleet of six open models
71–80 of 143 posts
Re: K2 Horizon: A connected fleet of six open models
#72My quick review of the 3.7B model (because I was interested) is that it's not to be trusted for coding. It failed my basic test I like to ask models and generated incorrect code. When prompted about the bug, it preceded to start hallucinating non-existent APIs. After doing that it got caught in a loop trying to desk check the solution that didn't work.
Not sure a model that small is really supposed to be used for any real coding. At that size you're usually using the model to do simple tasks like summarization.
Re: K2 Horizon: A connected fleet of six open models
#73My quick review of the 3.7B model (because I was interested) is that it's not to be trusted for coding. It failed my basic test I like to ask models and generated incorrect code. When prompted about the bug, it preceded to start hallucinating non-existent APIs. After doing that it got caught in a loop trying to desk check the solution that didn't work.
Not sure a model that small is really supposed to be used for any real coding. At that size you're usually using the model to do simple tasks like summarization.
To be clear, the question wasn't a complex one. It was more on the level of "could I use this for a fast inline coder" IE, single somewhat simple function question.
I wouldn't have dreamed to use this as an agent model.
7B models of the past have been able to pass this question. I've not tested it on a 4B model until now.
Re: K2 Horizon: A connected fleet of six open models
#74Earlier quoted context omitted.
The training data would need to have a permissive license for this to be possible.
Or, we just need to get this over with and declare any digital data findable via the internet to just be public property of everyone. Everything becomes public, besides stuff you keep locally, and there is no difference anymore, it's all just data anyone can use for whatever. A 1 year grace period for everyone to pull stuff off they don't want to be a part of this bright new open era, then we just scrap everything re…
What you're slightly more realistically looking for here is for publicly available data to have a Fair Use exemption for certain uses, which is certainly something worth discussing.
Re: K2 Horizon: A connected fleet of six open models
#75Earlier quoted context omitted.
The training data would need to have a permissive license for this to be possible.
Or, we just need to get this over with and declare any digital data findable via the internet to just be public property of everyone. Everything becomes public, besides stuff you keep locally, and there is no difference anymore, it's all just data anyone can use for whatever. A 1 year grace period for everyone to pull stuff off they don't want to be a part of this bright new open era, then we just scrap everything re…
I don't really get what you're suggesting. You give a 1 year grace period for Metallica to pull all its music off the Internet, but then as soon as I host some of their MP3s on my Wordpress blog it's "public property of everyone" from that point forward?
Re: K2 Horizon: A connected fleet of six open models
#76Earlier quoted context omitted.
I'd you have some tips for coming up with such tests, I would love to hear them. My Gmail username is the same as my HN username. Thank you!
It's actually just a coding interview test that I liked to ask in the past. You can find it and others on leetcode. The reason I personally like my question is because it's pretty close to some of the real world work we do. It's mostly mundane and easy to bang out, but really easy for someone to do a n log n solution where an n solution exists. A good example (but not my question) would be something like "I have a li…
LLMs have a problem with that type of question? I might try it later at home.
Re: K2 Horizon: A connected fleet of six open models
#77Earlier quoted context omitted.
It's actually just a coding interview test that I liked to ask in the past. You can find it and others on leetcode. The reason I personally like my question is because it's pretty close to some of the real world work we do. It's mostly mundane and easy to bang out, but really easy for someone to do a n log n solution where an n solution exists. A good example (but not my question) would be something like "I have a li…
LLMs have a problem with that type of question? I might try it later at home.
Now a days? No. It's actually getting to be a bad question because they all push out about the exact same answer.
But much earlier they did and, apparently, these really small models still do. At this point it serves as more of a smoke test for me. Success means little, failure means a lot.
Re: K2 Horizon: A connected fleet of six open models
#78Earlier quoted context omitted.
Or, we just need to get this over with and declare any digital data findable via the internet to just be public property of everyone. Everything becomes public, besides stuff you keep locally, and there is no difference anymore, it's all just data anyone can use for whatever. A 1 year grace period for everyone to pull stuff off they don't want to be a part of this bright new open era, then we just scrap everything re…
I'd prefer to stay within the [hacker ethics]( https://www.ccc.de/en/hackerethics ), and protect private data. For non-private/personal data, sure. But individual people need their privacy protected.
Me too, I'm hacker ethics all the way, which is why I'm saying anything network connected should really realize the "All information should be free." dream, and then private data should be far away from the internet, on computers/drives not even connected to the internet. The whole E2E encryption is a ticking time bomb people rely to keep their data safe from others, but nothing that you don't physically have close to you can be truly secret forever, and even then it'll be hard.
Re: K2 Horizon: A connected fleet of six open models
#79The Uno "diffusion adaptor" will take a while for me to understand, but sounds very interesting.
Re: K2 Horizon: A connected fleet of six open models
#80My quick review of the 3.7B model (because I was interested) is that it's not to be trusted for coding. It failed my basic test I like to ask models and generated incorrect code. When prompted about the bug, it preceded to start hallucinating non-existent APIs. After doing that it got caught in a loop trying to desk check the solution that didn't work.
7B produced 2 answers, 1 was correct though more expensive and the second was incorrect.
The first attempt with 7B the model got stuck in an infinite loop.