11–20 of 167 posts
This is precisely why they should really open source their model so that anyone can download and run it on their own infrastructure. Just like google or others have done and one is free to run it on their own laptop (some even without a GPU) , on premise or on any cloud provider infrastructure. They can continue to provide a hosted service for their model but they should allow it to be downloaded just like BERT.
With all of these outages, you have to wonder if it's a lack of skilled engineers on their part, or if they simply don't have enough GPUs to keep the lights on all the time.
This is precisely why they should really open source their model so that anyone can download and run it on their own infrastructure. Just like google or others have done and one is free to run it on their own laptop (some even without a GPU) , on premise or on any cloud provider infrastructure. They can continue to provide a hosted service for their model but they should allow it to be downloaded just like BERT.
I imagine the huge demand that ChatGPT is seeing would make any cloud vendor sweat if you were to suddenly lump it on top of the usual demand.
To me it's entirely unsurprising that OpenAI would have trouble keeping up. Good luck to them.
LLM's are incredibly expensive to run. I imagine the huge demand that ChatGPT is seeing would make any cloud vendor sweat if you were to suddenly lump it on top of the usual demand. To me it's entirely unsurprising that OpenAI would have trouble keeping up. Good luck to them.
Sending major hugs to their team, always hard to keep the lights on when I am sure that they are breaking scale records possibly every day.
This is precisely why they should really open source their model so that anyone can download and run it on their own infrastructure. Just like google or others have done and one is free to run it on their own laptop (some even without a GPU) , on premise or on any cloud provider infrastructure. They can continue to provide a hosted service for their model but they should allow it to be downloaded just like BERT.
It takes an additional fortune to pay humans to do RLHF (reinforcement learning from human feedback).
It takes an additional fortune to serve the model.
There are also researchers getting paid there that live in one of the most expensive hubs in the world.
This is precisely why they should really open source their model so that anyone can download and run it on their own infrastructure. Just like google or others have done and one is free to run it on their own laptop (some even without a GPU) , on premise or on any cloud provider infrastructure. They can continue to provide a hosted service for their model but they should allow it to be downloaded just like BERT.
This is precisely why they should really open source their model so that anyone can download and run it on their own infrastructure. Just like google or others have done and one is free to run it on their own laptop (some even without a GPU) , on premise or on any cloud provider infrastructure. They can continue to provide a hosted service for their model but they should allow it to be downloaded just like BERT.
It takes a fortune to pay for the computing infrastructure to train a model. It takes an additional fortune to pay humans to do RLHF (reinforcement learning from human feedback). It takes an additional fortune to serve the model. There are also researchers getting paid there that live in one of the most expensive hubs in the world.
This is precisely why they should really open source their model so that anyone can download and run it on their own infrastructure. Just like google or others have done and one is free to run it on their own laptop (some even without a GPU) , on premise or on any cloud provider infrastructure. They can continue to provide a hosted service for their model but they should allow it to be downloaded just like BERT.
Not sure why this gets downvoted. But sometimes HN just cannot take the truth.