mm_maybe

@mm_maybe@sh.itjust.works

• ⁨Comment⁩ on ⁨I'm sure everyone remembers⁩ ⁨⁨3⁩ ⁨weeks⁩ ago⁩:

  so which country do you hail from?

• ⁨Comment⁩ on ⁨This world is cruel…⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  The musical instrument thing is transitory and depends entirely on the instrument.

  Pre-relationship; in a popular band playing a more traditional instrument like guitar with a bunch of also attractive people (or at least part of a cool local scene) = hot

  In a relationship and/or solo bedroom producing any kind of electronic music and/or buying lots of synthesizers, drum machines or grooveboxes = not hot

  Also note how low “clubbing” is on the least attractive list, so no, DJs and electronic musicians who perform live don’t get a pass

• ⁨Comment⁩ on ⁨Not likely to be AI-generated or Deepfake⁩ ⁨⁨1⁩ ⁨month⁩ ago⁩:

  There are a bunch of reasons why this could happen. First, it’s possible to “attack” some simpler image classification models; if you get a large enough sample of their outputs, you can mathematically derive a way to process any image such that it won’t be correctly identified. There have also been reports that even simpler processing, such as blending a real photo of a wall with a synthetic image at very low percent, can trip up detectors that haven’t been trained to be more discerning. But it’s all in how you construct the training dataset, and I don’t think any of this is a good enough reason to give up on using machine learning for synthetic media detection in general; in fact this example gives me the idea of using autogenerated captions as an additional input to the classification model. The challenge there, as in general, is trying to keep such a model from assuming that all anime is synthetic, since “AI artists” seem to be overly focused on anime and related styles…

• ⁨Comment⁩ on ⁨Artifical Intelligence⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:

  I find it very funny that people are so concerned about false positives. Models like these should really only be used as a screening tool to catch things and flag them for human review. In that context, false positives seem less bad than false negatives (although, people seem to demand zero error in either direction, and that’s just silly).

• ⁨Comment⁩ on ⁨Artifical Intelligence⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:

  If you don’t mind, I’d be interested to see the images you used. The broad validation tests I’ve done suggest 80-90% accuracy in general, but there are some specific categories (anime, for example) on which it performs kinda poorly. If your test samples have something in common it would be good to know so I can work on a fix.

• ⁨Comment⁩ on ⁨Artifical Intelligence⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:

  Friendly reminder that my AI-generated image detector is available to use free of charge here: huggingface.co/spaces/umm-maybe/sdxl-detector

• ⁨Comment⁩ on ⁨every damn morning⁩ ⁨⁨2⁩ ⁨months⁩ ago⁩:

  Me: I’ve cut my coffee intake down to one cup a day! Look how disciplined and restrained I am!

  Also me: drinks 1.5 cans of Celsius per day

• ⁨Comment⁩ on ⁨Seriously, what the f*** is keeping Donald Trump in this presidential race?⁩ ⁨⁨3⁩ ⁨months⁩ ago⁩:

  It’s 100% this. Politics is treated like a sport in the USA; the only thing that matters is your side winning, and which side you root for is largely dictated by location and family history. This is encouraged by the private news media, who intentionally report on election campaigns in this manner in order to increase ratings and ad revenue. Social media only made it worse because it made a lot of abstract identity dimensions, such as political affiliation, feel stronger to people than their everyday lives.