71–80 of 696 posts
Earlier quoted context omitted.
This is actually a big deal. They erred on the side of caution, but as a result the responses are nerfed beyond basic "censorship" level. I saw someone describe this as "desperately posistive" and it really resonated with me. It produces underwhelming / unrealistic responses in negative scenarios.
It's just a matter of time before open source models show up with no limits whatsoever.
I think open-assistant.io has a chance to do exactly this. We'll see what kind of moves they make in coming months though, wouldn't be surprised if they go the safer route.
Earlier quoted context omitted.
Is there though? It's just a matter of swapping out $BASE_API_URL.
You have to rebuild all your prompts when switching providers.
This area by definition has no moats. English is not proprietary.
Use case is everything.
> It is priced at $0.002 per 1k tokens, which is 10x cheaper than our existing GPT-3.5 models. This is a massive, massive deal. For context, the reason GPT-3 apps took off over the past few months before ChatGPT went viral is because a) text-davinci-003 was released and was a significant performance increase and b) the cost was cut from $0.06/1k tokens to $0.02/1k tokens, which made consumer applications feasible wit…
How do these compare to the recent Default ("turbo") vs legacy" (for plus/pro) modes? If "turbo" is "gpt-3.5-turbo", how to access the (better?) "legacy" by API?
Earlier quoted context omitted.
This. Despite how impressive the results are, there isn't a particular large moat to prevent competitors from entering the space. Basically just compute $ for training.
they likely do lots of tricks and data collection inside which makes quality better.
Whisper as an API is great, but having to send the whole payload upfront is a bummer. Most use cases I can build for would want streaming support. Like establish a WebRTC connection and stream audio to OpenAI and get back a live transcription until the audio channel closes.
It's also annoying since there appears to be a hard limit of 25 MiB to the request size, requiring you to split up larger files and manage the "prompt" to subsequent calls. Well, somehow, near as I can tell, how you're expected to use that value isn't documented.