Live data from Hacker News

GPT is all you need for the back end

github.com

1–10 of 278 posts

Re: GPT is all you need for the back end

#5
post #2

Obviously a sensationalised title, but it's a neat illustration of how you'd apply the language models of the future to real tasks.

Would be ridiculously inefficient, while also being nondeterministic and opaque. Impossible to debug, verify, or test anything, and thus would be unwise to use for almost any kind of important task.

But maybe for a very forgiving task you can reduce developer hours.

As soon as you need to start doing any kind of custom training of the model, then you are reintroducing all developer costs and then some, while the other downsides still remain.

And if you allow users of your API to train the model, that introduces a lot of issues. see: Microsoft's Tay chatbot

Also you would need to worry about "prompt injection" attacks.

Re: GPT is all you need for the back end

#6
Of course this will only work if your user's state can be captured within the 4096 tokens limit or whatever limit your llm imposes. More if you can accept forgetting least recent data. Might actually be OK for quite a few apps.

Re: GPT is all you need for the back end

#8

how would storage work across sessions?

I'm 80% sure the article is just an interesting POC. That said, one of the more interesting things that has come with the "Shakespear Model" is the idea of context state. Basically remembering the conversation.

Something could be muddled together to correlate to a specific 'session-id'.

Security nightmare overall I guess but fun to play with.

Re: GPT is all you need for the back end

#9
Yes I could do that. I could indeed invoke something that requires god-knows how many tensor cores, vram, not to mention the power requirements of all that hardware, in order to power a simple CRUD App.

Or, I could not do that, and instead have it done by a sub-100-lines python script, running on a battery powered Pi.

Post reply on HN