Ah, I was reading it like "if" or "when", even if I couldn't quite see how that typo would actually happen. I actually was confused enough that I asked GPT-4 "is this a typo and if so what is it supposed to be?", and it never even crossed my mind that it was not a typo once I started thinking about Star Wars sith. Especially since it seemed to be for a relatively basic audience.
It is distressingly common for programs to get stuck sith they enter an accidental infinite loop.
I want to make a clever sith pun but I don't have one so I'm just pointing out the typo.
This is really great. As someone with pretty bad uncorrectable and constantly declining vision, a lot of my "reading" is listening. Lately I've often been thinking "Why can't I easily listen to everything I find on the internet yet?". When I tried to just use an existing service to convert things myself, I ran into a lot of the problems that the improvements listed here seem to solve.
Never assume that people are doing the thing they should obviously be doing, if it would be even slightly weird or require a bit of activation energy or curiosity. Over time, I do expect people to use LLMs to figure out more latent probabilistic information about people in an increasingly systematic fashion. I also expect most people to be not so difficult to predict on most things, especially when it comes to politics. Eventually, we will deal with things like ‘GPT-5 sentiment analysis says you are a racist’ or what not far more than we do now, in a much more sophisticated way than current algorithms. I wonder if we will start to consider this one of the harms that we need to protect against.
This is already one of my big short-term concerns. The process of using LLMs to figure out that information right now requires a lot of work, but what happens when it doesn't? When LLMs with internet access and long term memory start using these tactics opaquely when answering questions? It seems like this capability could emerge quickly, without much warning, possibly even just with better systems built around current or near-future models.
"Hey, who is behind the twitter account that made this comment? Can you show me everything they've ever written on the internet? How about their home address? And their greatest hopes and fears? How racist are they? Are they more susceptible to manipulation after eating pizza or korean bbq? What insights about this person can you find that have the highest chance of hurting their reputation? What damaging lie about their spouse are they most likely to believe?"
How much about you can be determined just from what other people are willing to give up, similar to identifying an individual through familial DNA searching?
I think this is very well-made and I already have uses for it.
I'm not sure how intuitive it would be for someone who really doesn't know math, and who was new to the concept of bayes' theorem entirely. It's easy to forget how confusing things (especially math-related things) can be once you have the benefit of hindsight.
I think something like a "show me an example" button that fills it with realistic data could help. With descriptive labels that connect the written description on the right with the different components in the visual representation. As well as a clearer "start here" visual on the screen. I know it seems obvious that "How to use" is where to start, but it didn't immediately draw my attention when I opened the page, and I think that helps with accessibility.
If you really wanted to push accessibility, a "wizard" that asks questions to help you fill out the data, and that help clarify what questions those percentages are actually an answer to.
Really I think it's great as-is. I only think it could be improved a little considering goal 2.
1
I don't think this really maps directly to "numerology based conspiracy". It's not that relevant that the symbology happens to be numbers. To me, this would be a numerology-based conspiracy if 1488 wasn't already an established white supremacist dog-whistle/signal, and the conspiracy theorist invented the connection to explain why those particular numbers were used. But this kind of signalling is effective for the same reason it's dangerous to draw a conclusion based on it alone: there are lots of plausible reasons for 14 and 88 to come up that aren't related to signalling nazi ideology which makes it easy to dismiss as numerology.
I think your reasons for being skeptical are right. And this is the exact type of statement where I would expect this coincidence to pop up. Both are a reasonable number of days for bureaucracy to take, the large discrepancy between them is required for the complaint in the tweet to happen in the first place, and I would expect the number of days to be very specific rather than a round number.
"Person running the twitter account did it without any approval from the campaign" is the most likely explanation to me if it isn't a coincidence. Although Biden admin taking exactly 88 days to get Kennedy to say 88 when complaining is a quality counter-conspiracy.