Hacker News Reader

Comment by Vetch | Hacker News Reader

Does it make sense to put this on the chrome store? OpenAI is eventually going to end the beta period or Azure will run out of GPUs, whichever is first, then it'll no longer be accessible.

In theory we can replicate this with GPT-3 but ChatGPT has better access to its knowledge, when it's not being a nagging busybody, which makes it much friendlier to interact with, when it's not being a nagging busybody.

View on HN

Now imagine a decentralized version of this, as in I have it locally, ask it a question and rate how helpful the answer was, then share this feedback with everyone and they update their model.

It does? I hooked up GPT3 to my discord server and can't really tell the difference in quality.

I assumed the ChatGPT3 enhancement is that they added memory of the dialogue to it? That's a huge improvement over one off questions and answers. You can tell it to correct its answers and ask follow up questions.

I wonder myself if the "memory" is just inputting the previous dialogue as input to every subsequent query. I think this would probably get quite slow after awhile however.

This is what it does. At least if you ask it how it does it. ;)

Probably, they're still using relatively simple queries. Maybe the memory is larger, but with 4096 tokens, GPT-3 is no slouch either. RLHF has tuned it so the conversational output of GPT is more inline with human expectation, it's also less likely to make glaring errors. The cost of their approach is it sometimes get stuck rephrasing things and wraps everything in boilerplate that can derail subsequent generation.

Reply on news.ycombinator.com