RE: Programming Diary #34: Your post now has a permanent payout window
I like it and there's plenty to think about in there.
As somebody who curates manually, and also likes your idea, what would the best way of supporting this be? Presumably in my case, I'm best to keep my STEEM Power, rather than delegate it to you? Although without a decent SP base, can thoth have a big enough impact?
Given that there are already people highlighting "active" content, should thoth focus on content that isn't active and has already paid out? This will make it unique on Steemit and therefore more attractive. In my opinion, this would also help to focus people on leaving something worth leaving, rather than something that is irrelevant as soon as the "POST" button is pressed. And should also improve the quality of what Thoth highlights.
Test examples of the Thoth output can be seen here for active posts and here for historical posts.
In my opinion, the posts selected don't highlight the best of Steem in the past or at present so I think the selection algorithm will need some adjustment. Proof of Concept though and in my opinion, it's looking good.
I'd also think about attention span. I'm not lazy but I'm "Time Poor". So it's too text heavy for my liking. I wonder if the "Target Audience" is necessary for each post? Perhaps a general theme for each grouping would suffice? Generally speaking, I'll read the post title and think "'Crafting the Murderers of Tomorrow, TODAY!'" - that sounds interesting (click bait at its finest - it wasn't) and "'How $PUSS Could Change Digital Identity In The Metaverse'" sounds like one of the Nigerian Crypto Experts that I caught plagiarising has moved on to AI content creation about subjects he knows little about.
In the case of the "Active" version, the presence of this single author would stop me from supporting the post - and therefore the other authors. (Although the ChatGPT post will get read once I finish replying to you.)
I also wonder if Thoth could self-learn by analysing the success of each post it produces? Not being biased towards particular authors (presumably highlighting an author would encourage them to vote) but based upon the content / tags that are used. It might learn that #gaming attracts more readers whereas #thediarygame doesn't - eventually leading to a weighted bias in content curated. You could even introduce some bias now based upon your own opinions of the /tags page.
Final thought - It's a shame that @thoth went to some pointless account 9 years ago.
The original thought was for active posts. In that case, I imagined that you'd be able to scan the output for posts that look interesting and then click through and support the featured authors directly. Now that historical posts are in the mix, it gets more complicated. Of course, you could vote the Thoth post - but I get that there may be disqualifying content in some. You could also use an eversteem style comment/beneficiary - mechanism to individually support any interesting paid-out posts that it highlights (maybe I could even consider adding one reply to the Thoth post with an individual beneficiary for each included author? Not sure if I like that idea, though...).
For historical posts, if I find a way to deal with the cap on beneficiaries, then hopefully Thoth can get enough delegated for passive income in order to make a difference. Besides ROI and user retention, I suppose there are may also be SEO benefits from resurfacing and relinking lost content(?), so passive investors have multiple self-interested reasons to delegate.
This is a good point. I think that's probably the case. At least near the beginning. It's funny how the project seems to be getting flipped upside down.
I completely agree. In addition to improving the post selection, I also need to stop it from picking the same post multiple times when someone edits an existing comment. The current version is definitely proof of concept.
Definitely possible in the future. @cmp2020 had a machine-learning voting bot running a couple years ago when he was in school. Eventually, that sort of selection could be inserted between the screening and the LLM - or before the screening. That's a long way down the road, though, I think.
I agree on this point, too. I should have mentioned that in the next steps section. I'm going to have a table near the front with just the titles, authors, dates, tags, and maybe 100 words from the body, then I'll put the AI output in a separate section - maybe another table. That way the reader can scan the summary table first and decide which of the AI summaries they want to read.
Include/exclude of tags is one of the screens that I'm still planning to add. I think bias is good. I'd like to see multiple instances of Thoth all running with their own unique biases and then the community can decide which ones are most valuable.
Yep. That was one of the first things I checked, too. Disappointing. I have an alternate in mind that is available, but @thoth would've definitely been ideal. Thank you for the feedback!
No - it feels a bit "spammy" and perhaps overkill. I think that once you get the algorithm right, then it probably wouldn't be necessary anyway.
It's certainly possible - especially if the post passes the "follow" links threshold (which I'll take a look at at some point because it feels unhelpfully high at the moment).
I think the benefit's 2-fold - it might help to index pages that might have previously been missed and it might also give that content greater weight because of additional internal links to it.
Either way, it shouldn't do any harm.
That's good - as the thoughts mature, the project will move in the right direction.
I can feel the potential with this project. Whilst I think that greed with the existing generation of voting bots will continue, this feels like a viable alternative that should benefit the "real Steemit community longer term.
Exactly what I was thinking (though at current limits it would buy me 30 or 35 more slots for delegator beneficiaries 😉).
That's what I'm hoping too.
That's how I feel, too. It's obviously not a panacea, but there's a huge amount of buried value out there that can strengthen the ecosystem if we figure out good ways to "mine" it.