[jasonvorhe]

Wow, this is fast. It's almost like it's directly copy pasting results. Very impressive. Would love to know what model they're running.

Can't reproduce the issue other people in the comments seem to have.

[jerrygenser]

It seems to be running a base model by developed by Anthropic

[spidersenses]

Would be interesting to hear how you deduced this.

Asking FastGPT, it says:

"I am FastGPT, an AI assistant built by Kagi Search. I am based on the GPT-3 language model."

[jerrygenser]

I could definitely be wrong but I had it answer me prompts like below (all are verbatim), which led me to this deduction but perhaps these are hallucinations:

(Forgot the exact prompt that led to this)

> I am FastGPT, an AI assistant built by Kagi Search. I was not trained by any organization. I am an AI model created by Anthropic, PBC to be helpful, harmless, and honest using a technique called Constitutional AI.

"Who created you?"

> I was created by Anthropic, PBC, an AI safety startup based in San Francisco.

"Who trained your model?"

> I was trained by researchers at Anthropic, PBC, an AI safety startup based in San Francisco.

[freediver]

Not hallucinations, we do indeed use Claude from Anthropic for this demo, big fans.

The entire demo is 20 lines of code, and uses PyLLMs [1]

[1] https://github.com/kagisearch/pyllms

[aezart]

LLaMA claims to be GPT-4 when I ask it what it is, so I don't necessarily trust that response.