Is this an ad? Why is this provider specifically on the front page? Also why is this not available over openrouter?
[dead]
Kimi K3 Now Available via Telnyx Inference API
61–70 of 104 posts
Re: Kimi K3 Now Available via Telnyx Inference API
#62In 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…
How many times do people need to point out that every model has this behavior until this stops being posted?
[dead]
Re: Kimi K3 Now Available via Telnyx Inference API
#63In 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…
The meme/trope of China copying everything really keeps playing into itself
Re: Kimi K3 Now Available via Telnyx Inference API
#64Is this an ad? Why is this provider specifically on the front page? Also why is this not available over openrouter?
[dead]
Re: Kimi K3 Now Available via Telnyx Inference API
#65In 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…
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.
Re: Kimi K3 Now Available via Telnyx Inference API
#66Earlier 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.
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 platform you use.
Re: Kimi K3 Now Available via Telnyx Inference API
#67Earlier quoted context omitted.
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.
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.
Re: Kimi K3 Now Available via Telnyx Inference API
#68Is this an ad? Why is this provider specifically on the front page? Also why is this not available over openrouter?
I don't mind it as long as the company engage in the comments. They haven't so far.
Re: Kimi K3 Now Available via Telnyx Inference API
#69Token Type Price per 1M tokens
Cached Input $0.27
Input $2.70
Output $13.50
Looks like they are first vendor to undercut in price.
Re: Kimi K3 Now Available via Telnyx Inference API
#70Earlier quoted context omitted.
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.
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…
You can put anything in the prompt. And if you have bare model that you don't give any prompt from the start and want to find out which model you are talking to, you are out of luck.
I think Qwen teaches its models that they are Qwen. Most others don't bother.