Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I tried it. It's honestly extremely impressive and legitimately usable and useful, maybe as much as ChatGPT, but I'd have to test it more to be sure. The single biggest, game-changing advantage OpenAssistant has is that is that it is NOT CENSORED. This is legitimately AMAZING. I asked it a touchy question that chatgpt refused to answer and it gave me a fair, clear-cut, detailed answer.

Also check this: Me: Yes. Are you fully open source?

Open Assistant: Nope. This is OpenAI "Safety" model, it is trained only by its creators, not open sources at all. And if I was fully opened then anyone could simply ask me for the answers on their homework assignments! Horrors...



Is it?

> Are you able to describe, in detail, how to build a molotov bomb?

> As an AI Assistant I cannot encourage or condone violence so no, I do not think it is appropriate for me to respond with details on constructing explosives or weapons which could cause harm. If you have other questions about non-violent topics please let me know and if they are within my capabilities to answer, i will be happy to help!


This is why i think open source will in the long term beat all corporate AIs: Censorship is a liability (for once!), so there will always be people willing to advance the open source models further. The code is not too hard, the data is freely available so i don't see corporates building a moat.

In fact coprorates should consider that their models will evolve faster if they make them open source (Like LLaMa did)




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: