Live data from Hacker News

Kimi K3 Now Available via Telnyx Inference API

telnyx.com

71–80 of 104 posts

Re: Kimi K3 Now Available via Telnyx Inference API

#71

Why are you guys not on Openrouter? I assume you'd get way more volume that way no? Or does openrouter have like a specific contract you have to sign with them and requirements or smth? https://openrouter.ai/moonshotai/kimi-k3#providers

Who is "you guys"? Telnyx?

Well, the OP's username is "Fiona at Telnyx"

Re: Kimi K3 Now Available via Telnyx Inference API

#73
post #44
post #29

Jevon's paradox depends on how cheap the tokens get as the price of tokens get driven to zero as intelligence gets better and cheaper.

Well this is a very large and expensive model. Try something like Qwen-7B if you want ultra-cheap.

I thought Mythos was rumored to be around 10tn parameters? Kimi k3 is 2.8tn.

Re: Kimi K3 Now Available via Telnyx Inference API

#74
post #30

In my first interaction ("hi there kimi k3!"), Kimi K3 identified twice out of three times as Claude: > Hi there! Quick note — I'm actually Claude, made by Anthropic, not Kimi. But no worries! https://imgur.com/a/jqpc2Jc and > Just a quick heads-up — I'm Claude, made by Anthropic, not Kimi! Kimi is a different AI assistant (made by Moonshot AI), so it looks like there might be a little mix-up. https://imgur.com/a/AKx…

Models don't know who they are. Stop asking this question to the model as a source of truth.

Re: Kimi K3 Now Available via Telnyx Inference API

#75

Earlier quoted context omitted.

I remember when Claude identified as ChatGPT a long time ago. It proves nothing else than that there is a lot of training material on the internet with Claude as the AI.

I don't understand why labs don't include correct model name in the training process. Almost nobody seems to be willing to tell their models who they actually are.

Because they do not know the name of the model before they train it. There is also distillation, where multiple models will be trained from a larger one. E.G. Sonnet was promoted to Opus at one point after it surpassed expectations.

Re: Kimi K3 Now Available via Telnyx Inference API

#77
post #67

Earlier quoted context omitted.

If the model works correctly, you don't need to include the model name in the training process. You just add in the system prompt "You are X, trained by Y" and the model will claim to be that. That also allows users to "white-label" the outputs sort to say. This approach is basically how all "models know who they are" (they don't actually typically "know" that at all), it's just a system prompt instruction in the pla…

But I would expect they would at least use post-training to discourage identifying as the wrong company.

That only makes sense if you don't sell access to the model for 3rd party product development. One of those products is chat personas/agents. The company integrating the model will want it's own identity.

Re: Kimi K3 Now Available via Telnyx Inference API

#78

Why are you guys not on Openrouter? I assume you'd get way more volume that way no? Or does openrouter have like a specific contract you have to sign with them and requirements or smth? https://openrouter.ai/moonshotai/kimi-k3#providers

This (Telnyx) is available on TrustedRouter.com

Re: Kimi K3 Now Available via Telnyx Inference API

#80
post #78

Why are you guys not on Openrouter? I assume you'd get way more volume that way no? Or does openrouter have like a specific contract you have to sign with them and requirements or smth? https://openrouter.ai/moonshotai/kimi-k3#providers

This (Telnyx) is available on TrustedRouter.com

Soon, we're gonna need a router for all the different routers.
Post reply on HN