Hacker News Reader

Comment by x86hacker1010 | Hacker News Reader

Shouldn’t this title be - build a webapp using ChatGPT API?

Yeah that was disapointing given the title. ChatGPT didn't spring full-formed out of nowhere. It's progress upon an existing body of work that is totally opaque to the uninitiated but a reasonable facsimile can be approximated out if you spend enough time on the right discords and http://huggingfaces.co and Google Colab. ML algos and their results shouldn't be limited to an Ivory tower of Arvix papers.

FYI ChatGPT does not have an API and the article references GPT-3 general availability release.

ChatGPT runs on a heavily modified version of GPT3 nicknamed “GPT3.5” that is also not available via API.

No, because there is no (public) chatGPT api. This is using the GPT-3 API to build something that behaves similarly to chatGPT.

I wonder if one of the open models would work the same

I tried them all, and continue trying when new things come out. No open model is capable of even remotely approaching the capabilities of GPT-3 or ChatGPT. Even if you had an equivalent trained model, running it would require enormous hardware.

While Stable Diffusion is pretty comparable to DALL-E 2 even on small hardware (such as M1 MacBook Air), this doesn't hold true for large language models. These need much, much more VRAM.

text-davinci-003 is extremely close, or code-davinci-002

None of that model available to run on your hardware

thats a real shame. Any idea why GPT-3 generations differ so much? Maybe eleuther/whatever could look at refining their model in a similar way.

It's most likely because of the actual runtime size of the model. All the open models are sized for consumer-grade devices, and thus 10x-100x smaller than whatever OpenAI runs (probably around 100+ GB in VRAM, maybe even some multiples more). This is one of the main reasons why their API makes business sense - it's not practical at all to run models like GPT-3 yourself, and training them costs incredible amount of money too.

Reply on news.ycombinator.com