No Stupid Questions
No such thing. Ask away!
!nostupidquestions is a community dedicated to being helpful and answering each others' questions on various topics.
The rules for posting and commenting, besides the rules defined here for lemmy.world, are as follows:
Rules (interactive)
Rule 1- All posts must be legitimate questions. All post titles must include a question.
All posts must be legitimate questions, and all post titles must include a question. Questions that are joke or trolling questions, memes, song lyrics as title, etc. are not allowed here. See Rule 6 for all exceptions.
Rule 2- Your question subject cannot be illegal or NSFW material.
Your question subject cannot be illegal or NSFW material. You will be warned first, banned second.
Rule 3- Do not seek mental, medical and professional help here.
Do not seek mental, medical and professional help here. Breaking this rule will not get you or your post removed, but it will put you at risk, and possibly in danger.
Rule 4- No self promotion or upvote-farming of any kind.
That's it.
Rule 5- No baiting or sealioning or promoting an agenda.
Questions which, instead of being of an innocuous nature, are specifically intended (based on reports and in the opinion of our crack moderation team) to bait users into ideological wars on charged political topics will be removed and the authors warned - or banned - depending on severity.
Rule 6- Regarding META posts and joke questions.
Provided it is about the community itself, you may post non-question posts using the [META] tag on your post title.
On fridays, you are allowed to post meme and troll questions, on the condition that it's in text format only, and conforms with our other rules. These posts MUST include the [NSQ Friday] tag in their title.
If you post a serious question on friday and are looking only for legitimate answers, then please include the [Serious] tag on your post. Irrelevant replies will then be removed by moderators.
Rule 7- You can't intentionally annoy, mock, or harass other members.
If you intentionally annoy, mock, harass, or discriminate against any individual member, you will be removed.
Likewise, if you are a member, sympathiser or a resemblant of a movement that is known to largely hate, mock, discriminate against, and/or want to take lives of a group of people, and you were provably vocal about your hate, then you will be banned on sight.
Rule 8- All comments should try to stay relevant to their parent content.
Rule 9- Reposts from other platforms are not allowed.
Let everyone have their own content.
Rule 10- Majority of bots aren't allowed to participate here.
Credits
Our breathtaking icon was bestowed upon us by @Cevilia!
The greatest banner of all time: by @TheOneWithTheHair!
view the rest of the comments
Yes, this is exactly what I've found them to be the most useful for.
Here's a list:
Lemmy will hate me for this, but it remains the best chat it there is, especially if you subscribe to the pro version. There's different models but essentially it's just a good bot that will be really helpful giving you feedback on thoughts and ideas.
A to A- tier
Google AI chat bot which seems to be well received recently. I will be an asshole an assume it's not gonna be quite as good but it looks like they're sticking out now.
A- to B+ tier
Microsoft's AI attempt. It is an AI but it's only OK. Might get enough out of it for your purpose but it already has a long list of hiccups recorded so this is not something I would hang my head on all the time. Because it's got bing integration, generally the AI assisted search can be helpful though.
B tier
Basically an open source alternative to ChatGPT done well, although not quite as good. This Facebook's work which they are graciously providing free of charge for everyone to enjoy and tinker with. Huggingface is great because you will always find live demos of all the models there so if you are not a power user, in a limited way you can use this model on the website.
Between B and C tier
Llama is open source so it is possible to set it up yourself. Using the webui it is possible to do this on your own PC, removing the limitations for conversation speed and message counts. You will be struggling if your graphics card can't entertain the model though (good models eat vram for breakfast). If you have it setup, you will always get the best experience out of the Llama models which might make this worth it.
C tier
Other than those there are a lot of sites offering subscriptions to what is basically a different frontend for chatgpt or other open source models, which is arguably worse than all the options mentioned. There might be some gems in the rough but I haven't looked too far into it. This should give you an introductory overview though which is presumably more helpful to you.
I personally use ChatGPT and I am starting to appreciate it a lot. It does still lead ahead of Llama or anything else.
After reading your comments, it looks like what you're looking for is an AI that remembers your conversations. Generally an AI can only "remember" a specific amount of tokens (words iirc) and it will have amnesia about the rest.
I think the bigger Llama models will have high token cutoff as well as copilot (?) don't quote me on that tho.
We're not at the point where an AI will remember details for over a year from one conversation but if you always open a new conversation for a specific topic, you will already be able to get 90% of the way to where you want.
Good luck on your endeavors ;)
I think the benefit of third party AI services is exactly a way around that limited context window. The service can summarize the previous conversations and key facts about the user, store it and feed that back into the AI prompt.
Instead of wasting most of the context window for pages and pages of conversation, it can just prompt the AI with something like "the user is called Timmy, he works as an accountant, he has a girlfriend called Tammy, yesterday he told you that he thinks about proposing.".
I think even ChatGPT does something like that, but as it's a very general tool it might not be the best in filtering out information that is relevant for a "personal" conversation.