Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Run and create custom ChatGPT-like bots with OpenChat

github.com

Post reply on HN
Print view View original

51–60 of 63 posts

Re: Run and create custom ChatGPT-like bots with OpenChat

#51

Post by killthebuddha »

jerpint wrote: post #33

> Each chatbot has unlimited memory capacity, enabling seamless interaction with large files such as a 400-page PDF. How is this possible? Do they do fancy tricks at inference?

I've scanned the codebase and IMO the statement is mostly misleading. I think LangChain agents (which this is a thin wrapper around) do have some default compression/reranking behavior to help fit relevant context into the context window, but it's very, very, very far from actually infinite short-term memory.

I think the framing where the statement could be considered true is if you assume "memory = persistent storage", which is IMO not what most people will do.

Note: I'm not trying to imply the authors are being intentionally misleading.

Re: Run and create custom ChatGPT-like bots with OpenChat

#52

Post by ShakataGaNai »

If I understand what this tool is doing, there is an important security caveat.

>providing PDF files, websites, and soon, integrations with platforms like Notion, Confluence, and Office 365.

Means that anything you feed this ChatBot, gets turned into data that's uploaded to OpenAI. So if you're using an internal Confluence, consider all that data public now. We've already seen intranet pages show up on ChatGPT/OpenAI in the past.

Re: Run and create custom ChatGPT-like bots with OpenChat

#53

Post by naiv »

ShakataGaNai wrote: post #52

If I understand what this tool is doing, there is an important security caveat. >providing PDF files, websites, and soon, integrations with platforms like Notion, Confluence, and Office 365. Means that anything you feed this ChatBot, gets turned into data that's uploaded to OpenAI. So if you're using an internal Confluence, consider all that data public now. We've already seen intranet pages show up on ChatGPT/OpenAI…

The OpenAI API does not use the data for training.

Re: Run and create custom ChatGPT-like bots with OpenChat

#54

Post by iamflimflam1 »

ShakataGaNai wrote: post #52

If I understand what this tool is doing, there is an important security caveat. >providing PDF files, websites, and soon, integrations with platforms like Notion, Confluence, and Office 365. Means that anything you feed this ChatBot, gets turned into data that's uploaded to OpenAI. So if you're using an internal Confluence, consider all that data public now. We've already seen intranet pages show up on ChatGPT/OpenAI…

This simply isn't the case and people need to stop repeating it without doing some research first.

https://openai.com/policies/terms-of-use

    Use of Content to Improve Services. We do not use Content that you provide to or receive from our API (“API Content”) to develop or improve our Services. We may use Content from Services other than our API (“Non-API Content”) to help develop and improve our Services. You can read more here about how Non-API Content may be used to improve model performance. If you do not want your Non-API Content used to improve Services, you can opt out by filling out this form. Please note that in some cases this may limit the ability of our Services to better address your specific use case.

Re: Run and create custom ChatGPT-like bots with OpenChat

#56

Post by ShakataGaNai »

iamflimflam1 wrote: post #54
ShakataGaNai wrote: post #52

If I understand what this tool is doing, there is an important security caveat. >providing PDF files, websites, and soon, integrations with platforms like Notion, Confluence, and Office 365. Means that anything you feed this ChatBot, gets turned into data that's uploaded to OpenAI. So if you're using an internal Confluence, consider all that data public now. We've already seen intranet pages show up on ChatGPT/OpenAI…

This simply isn't the case and people need to stop repeating it without doing some research first. https://openai.com/policies/terms-of-use Use of Content to Improve Services. We do not use Content that you provide to or receive from our API (“API Content”) to develop or improve our Services. We may use Content from Services other than our API (“Non-API Content”) to help develop and improve our Services. You can read…

The research was seeing intranet sites cited by OpenAI. So maybe someone copied and pasted it into the web interface. Maybe the big multi-national firms had their intranet exposed to the internet. I don't know how it got there; heck, no one may know.
Post reply on HN