tilschuenemann

author here: Hey, that's my post on the frontpage, what is it doing here?!?

I've been working on my blog lately, and having only a few posts up and no readership, I'm now blown away by all the comments and mails and support I'm receiving. Thank you so much everybody!

It's a privilige to live in Germany, where I have public health insurance, and access to great doctors and staff. I'm tapering off the cortisone right now (I'll be taking it for six weeks in total, so I dodge a lot the strain it can have), and am now on another medication. I don't feel comfortable sharing my condition / medication due to me being on the job hunt, but maybe one day. Thanks for all the pointers, too.

Yes, it's worse for screenreaders, I listed that next to other drawbacks which I acknowledged. I don't intend to apply this method anywhere else due to these drawbacks, because accessibility matters.

It's a proof of concept, and maybe a starting point for somebody else who wants to tackle this problem.

Can LLMs detect and decode the text? Yes, but I'd wager for the case that data cleaning doesn't happen to the extent that it decodes the text after scraping.