I’m sure you know, but you’re probably going to get a lot of grief for this. I’m deeply suspicious of any new AI tool, especially one that tries to get in between me and my news (looking at you Feedly), and I’m sure I’m not the only one. So if you’re not already, I’d prepare yourself for a lot of strong emotions, and probably not in a good way.
If you wanted to get ahead of that kind of thing, you might want to explain what kinds of safeties you’re building into it. For example, on your roadmap you say want it to “Generate argument of for and against perspective then summarise the result of the 2 arguments.” This kind of thing in particular is quite risky. Any time you try to introduce value statements into an LLM summary, you’re in the danger zone. Even if you’re just trying to summarize the actual perspective of the piece, you’re basically just begging the LLM to hallucinate. But asking it to summarize hypothetical opposing arguments is just asking for trouble.
I could go on, but I don’t want to start a pile on. I appreciate when folks try to build cool stuff, you’ve just waded into some choppy waters…
I come back to this problem every year or so because I’m never satisfied with my music metadata. Years ago I had my musicbrainz picard settings dialed in really nicely, where I could drag folder over and it would spit out the right thing like 7 out of 10 times. It still required a lot of doubled checking and manual oversight though, so I was never satisfied.
I tried mediamonkey for a while, because it has decent metadata support and plugs into most of the expected APIs. But when all is said and done, all these tools use the same data sources, and none of them are exactly consistent with each other so matches aren’t as straightforward as they should be.
Lidar never quite did it for me, so I haven’t looked at my install in a couple years. But based on @skoberlink@lemmy.world’s recommendation I’ll try a fresh install and see if get I better results this time. I’m always happy in the arr interfaces.