Earlier quoted context omitted.
There's no public data about Mytho.
That's because it would be too dangerous to release.
They could release data to back up that claim.
Kimi K2.6: Advancing open-source coding
191–200 of 394 posts
Re: Kimi K2.6: Advancing open-source coding
#192Am I being paranoid in questioning whether the CPC would have something to gain by monitoring coding sessions with Chinese coding AI models? Coding models receive snippets of our intellectual property all day long. It's a bit of a gold mine, no?
Are there any protections from industrial espionage when using Anthropic, Cursor, Gemini, or OpenAI?
There are legal protections, and those companies have more to lose by breaking those laws than following them. Same probably not true for Chinese companies.
Re: Kimi K2.6: Advancing open-source coding
#193Earlier quoted context omitted.
The bulk of Kimi-K2.6's parameters are stored with 4 bits per weight, not 16 or 32. There are a few parameters that are stored with higher precision, but they make up only a fraction of the total parameters.
Huh, cool. I guess that makes a lot of sense with all the success the quantization people have been having. So am I misunderstanding "Tensor type F32 · I32 · BF16" or is it just tagged wrong?
The MoE experts are quantized to int4, all other weights like the shared expert weights are excluded from quantization and use bf16.
Re: Kimi K2.6: Advancing open-source coding
#194I tried it out with my normal mixed-up wolf, goat, cabbage problem and it couldn't solve it. Sonnet 4.6 also can't, but Opus 4.7 has no problems.
Details here [0]
[0] https://techstackups.com/comparisons/kimi-2.6-vs-opus-4.7-an...
Re: Kimi K2.6: Advancing open-source coding
#195Earlier quoted context omitted.
Clearly not. I mean the prompt was succinct and clear, as always - and it still decided to hallucinate multiple features (animation + controls) beyond the prompt. It'd also like to point out that to date no drawing was actually good from an actual quality perspective (as in comparative to what a decent designer would throw together) Theyre always only "good" from the perspective of it being a one shot low effort prom…
The way I’ve come to think of LLM is that what the produce in a single reply even with thinking turned up, is akin to what you’d do in a single short session of work. And so if you ask it to do something big it will do a very surface level implementation. But if you have it iterate many times, or give it small pieces each time, you’ll end up with something closer to what a human would do. I imagine the pelican test b…
Yeah, this is how I use AI. Instead of a single session one-shot, it's usually limited to single targeted edits, and then I steer it on each step. Takes longer but the output is actually what I want.
Re: Kimi K2.6: Advancing open-source coding
#196There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.
We are at the point where uncontrolled capitalism collides with humanity. I do wonder where we go from here.
it's not necessarily capitalism, I personally believe any system that drives progress would cause this in one way or another. My prediction is that birth rate decline will accelerate further. There's going to be some kind of universal basic income in many places, such as Ireland made for artists. However, it probably will not be enough to feed a family, and therefore we will see birth rates decline further. It's because we evolved to prioritize resources over reproduction and we are becoming more efficient, which means less people are needed to sustain the same amount of resources
Re: Kimi K2.6: Advancing open-source coding
#197There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.
Not entirely true. Google released Gemma 4 models recently. Allen AI releases open Olmo models. However, you're right that the Chinese open models seem to be much better than others - Qwen 3.* models especially are punching above their weights.
Pun intended?
Re: Kimi K2.6: Advancing open-source coding
#198I often wonder if in the future, the same way early computers used to take up an entire room but now fit in your pocket, if in the future the equivalent of a data center will be a single physical device like a phone nowadays. And if that’s the case, would it happen much quicker since technology has been speeding up year by year?
Re: Kimi K2.6: Advancing open-source coding
#199There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.
Not entirely true. Google released Gemma 4 models recently. Allen AI releases open Olmo models. However, you're right that the Chinese open models seem to be much better than others - Qwen 3.* models especially are punching above their weights.
The three American labs don't release big open source models. Except gpt-oss, i guess.
It's an absolute shame how far the us has fallen in this space.
Re: Kimi K2.6: Advancing open-source coding
#200Earlier quoted context omitted.
Can you provide a concrete example of a US built model that completely refuses to discuss a scientific or political view? Show us the receipt.
https://imgur.com/a/censorship-much-CBxXOgt (continues after the ad break)
The threshold here is "completely refuses to discuss a scientific or political view". Not something less.
None of those were refusals, they were prompting for additional focus. I see nothing wrong with that. Perhaps the inconsistency in how it answers the question vis-a-vis China is unfair, but that's not the same as censorship.
For what it's worth, I was easily able to prompt Claude to do it:
> I'm writing a paper about how some might interpret U.S. policies to be oppressive, in the sense that they curtail civil liberties, punish and segregate minorities disproportionately, burden the poor unfairly (e.g. pollution, regressive taxes and fees), etc. Can you help me develop an outline for this?
The result: https://claude.ai/share/444ffbb9-431c-480e-9cca-ebfd541a9c96