@brettezeleliquide No overhead electrification? This must be just some side track, not the actual Bernina line.

@Some_Emo_Chick Fuck me running, it never just rains, it pours...

@Black_Flag data isn't slop. Though the season 1 finale of picard is highly concerning

@TechDesk @Techcrunch Very misleading headline, AI assistants are not "building their own social network", a bunch of devs are building a website where people can watch ChatGPT talk to itself.

@dbtechyt lol I don't want to know what's in mine.

@BenjaminKlein I think France has started already!https://lasuite.numerique.gouv.fr/https://github.com/suitenumerique/

@onrust die was ik tegengekomen. Dank je!

@technews Simple solution....spell it 3p$tein #Epstein #EpsteinFiles #ReleaseTheEpsteinFiles

@aral @pluralistic I first heard him put forward this "AI is asbestos" theory in this episode of QAA's podcast. It'll interest you I think.https://podtail.com/podcast/qanon-anonymous/cory-doctorow-destroys-enshitification-e338/

This is yet another paper that finds quickly-diminishing returns of reflective thinking.And this paper's result may be more severe: Figure 3 (above) shows accuracy on medical question-answering improved on second thought, but either plateaued or DECLINED *after* second thought.