Human heuristics for AI-generated language are flawed · HackerPapers discussions

Human heuristics for AI-generated language are flawed — HN submission

Wed, 22 Mar 2023 17:40:56 GMT

Study: We can't distinguish AI vs. human self-presentations

1 point; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Human heuristics for AI-generated language are flawed — mentioned by ftxbro

Wed, 22 Mar 2023 17:30:13 GMT

I wanted to check this. So I tracked down the pnas paper from the press release article, and then I tracked down the 32 page arxiv paper from there https://arxiv.org/abs/2206.07271 and it still doesn't answer this question from my understanding of the paper. Its main point is "In our three main experiments, using two different language models to generate verbal self-presentations across three social contexts, participants identified the source of a self-presentation with only 50 to 52% accuracy." They did clarify that their data sets were constructed to be 50% human and 50% AI generated. But…

Paper and discussion history. A mention is not an endorsement.

Human heuristics for AI-generated language are flawed — HN submission

Wed, 08 Mar 2023 00:00:18 GMT

Human Heuristics for AI-Generated Language Are Flawed

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Human heuristics for AI-generated language are flawed — mentioned by pharrington

Sat, 18 Jun 2022 17:57:02 GMT

Their preprint is at https://arxiv.org/abs/2206.07271

Paper and discussion history. A mention is not an endorsement.