I know what information I can find on Wikipedia and I know that I can find additional information in the sources. Obviously I do not only use Wikipedia.
Not sure if you’re joking, but that is what I’d want. A very samll / compact, open source/weights AI model that runs locally, can interpret what I’m looking for and then queries encyclopedias, or a local wikipedia, science paper abstracts, articles and search backends (ideally EU funded) to find the shit I’m looking for. Including sources to back up what it’s telling me.
We need to somehow democratize search engines and AI models could be immensely useful for this. Even just filtering out the AI slop. Too bad there was such a kneejerk backlash to AI in firefox.
There isn’t any lightweight local LLM which give valid results, or you dedicate >90GB for it, or you permits that it connect to the online source servers, wasting a lot of bandwith. You can use locally only AIs dedicated to certain tasks, eg for summarizing documents or in some graphic apps to automate some functions or for accounting in the office, but forget an local alround Assistant.
If you want an AI for certain tasks, use search assistants, like DuckAI or Andisearch, which are good for summarize results fom Webpages without the need of big and large lengage models, being privacy friendly, or use a specific one which you can anonym without account, eg one of those from HuggingFace or one specific from Futurepedia, there you can filter what you need.
We already have this! It’s called a tool harness, and basically any kind of local agent framework supports it already, as well as a whole slew of locally runnable LLMs in every size.
AI implementation in every Browser has me looking up information direktly on wikipedia.org without going through a search engine first.
Most information isn’t on Wikipedia
I know what information I can find on Wikipedia and I know that I can find additional information in the sources. Obviously I do not only use Wikipedia.
A lot of it is: one just has to look for it a bit.
No, Wikipedia only gives a brief descriptionof a topic. When you want anything detailed you have to go to a better source.
Not sure if you’re joking, but that is what I’d want. A very samll / compact, open source/weights AI model that runs locally, can interpret what I’m looking for and then queries encyclopedias, or a local wikipedia, science paper abstracts, articles and search backends (ideally EU funded) to find the shit I’m looking for. Including sources to back up what it’s telling me.
We need to somehow democratize search engines and AI models could be immensely useful for this. Even just filtering out the AI slop. Too bad there was such a kneejerk backlash to AI in firefox.
There isn’t any lightweight local LLM which give valid results, or you dedicate >90GB for it, or you permits that it connect to the online source servers, wasting a lot of bandwith. You can use locally only AIs dedicated to certain tasks, eg for summarizing documents or in some graphic apps to automate some functions or for accounting in the office, but forget an local alround Assistant.
If you want an AI for certain tasks, use search assistants, like DuckAI or Andisearch, which are good for summarize results fom Webpages without the need of big and large lengage models, being privacy friendly, or use a specific one which you can anonym without account, eg one of those from HuggingFace or one specific from Futurepedia, there you can filter what you need.
We already have this! It’s called a tool harness, and basically any kind of local agent framework supports it already, as well as a whole slew of locally runnable LLMs in every size.