saltsaman

...Aaand It's Gone!

So it is a confirmed leak and they are just doing damage control?

Couple of things:

1. Filtering by model should be enabled by default. Mixtral-8x7b-instruct on Perplexity is almost as fast as the 7B Llama 2 on fireworks, but are quite different in sizes.

2. Pricing is a very important factor that is not included.

3. Overall service reliability should also be an important signal.

The problem is that they claim to have developed a groundbreaking Large Action Model when in fact it's just a playwright wrapper

Isn't the secret sauce just VNC with playwright? What more do you need to achieve 80% of what they are showcasing (basic doordash orders, spotify controls)?

Hi Peter, at which stage should a founder apply to O1?

I can see people training loras this way, which allows for multiple API function calls