Clarify meaning of "deeply integrated AI and semantic document tools" in FAQ

[WesleyAC]

The Nyxt FAQ writes:

Nyxt is a browser with deeply integrated AI and semantic document tools that work as a second brain to help you process and understand more, more quickly.

But from reading the manual and issue tracker it's somewhat unclear what this means. My guess is that it's either trying to ride hype (for funding or something?) or that it's a meme based on lisp being the language of the 60's AI boom, but it's unclear to me, and certainly my first guess at what this meant is that it comes with LLM integrations or something — it was only searching the manual and issue tracker that convinced me that probably wasn't the case.

What is this sentence meant to mean, and could it be clarified or removed?

For some context, if there is any kind of LLM integration or plan for such, I'd be uninterested in trying Nyxt, so having that as the first thing on the FAQ page is a huge red flag for me — it either means that Nyxt isn't something I want (fine, but that doesn't look like the case), or that the initial FAQ entry is highly misleading, which also doesn't make me trust this project.

I'd also appreciate clarity on whether you have future plans for "AI" (LLM, etc) integrations.

[WesleyAC]

#2166 has some related discussions. highlighting some relevant bits from @lansingthomas that might be relevant to other people who care about this:

Nyxt blends other tools into a single tool {window managers, text editors, AI tools, ...}

knowledge extraction engine sounds better to me.

• I have heard John pitch this and it seems like an effective way to converse about HOW Nyxt is helpful, for those who already align with our values.

• a knowledge extraction engine seems like it works out of the box. I don't feel the need to hack it before it works. This is very good.

• Engines are clean, precise, modern, complex yet useful. Fuel in → power out. Nyxt is like data in → knowledge out.

Classifies data/information {builds models of understanding}

extracts information from the Internet

[jmercouris]

The gist is this:

we have a lot of tools built in to our analysis library, pagerank, tf/idf, things like this which we can use to generate summaries, extract, keywords etc. There isn't a giant opaque LLM behind everything. These tools are used in logical ways, for example, when you bookmark something, how should you tag it? Nyxt figures out some likely tag candidates and suggests them to you.

[lansingthomas]

@WesleyAC I really appreciate Issues about the copy and messaging. These things really help our cause.

Maybe we can make it slightly better today. I have some ideas but I would love to hear yours before I share.

1. How would you change that 2 sentence answer to the question; What is Nyxt??

or perhaps,

2. If you HAD to change some elements of the answer what would they be? And more importantly, which elements of that answer should NOT change?