|
| ▲ | debugnik an hour ago | parent | next [-] |
| That barely anyone with an organic brain would use any those phrases as a heading, much less all of them. This article isn't particularly egregious but AI does come up with really cringy headings. Most often "the <irrelevant noun>" over and over. |
| |
| ▲ | fc417fc802 22 minutes ago | parent [-] | | The current frontier models also have a bizarre tendency to prepend said headings with weirdly irrelevant emoji. I really wonder where they picked that up. |
|
|
| ▲ | f311a an hour ago | parent | prev | next [-] |
| Do no try to look at the individual examples, look at the overall style of headings.
It's about style, people say such things, they are not unique. |
|
| ▲ | mock-possum an hour ago | parent | prev | next [-] |
| The point is not that no one says these IRL, the point is that LLMs always tend to fall back on this kind of verbiage - they got it from us, they aren’t doing anything new or special, they’re just predisposed towards a very particular kind of voice / word choice in prose. |
|
| ▲ | phatskat an hour ago | parent | prev | next [-] |
| I will echo the flagged comment in spirit: Those are wild headings that read like an op-ed on a site covered in ads. I've said some of those things irl, and "relief pitcher" is a thing, and in solution those phrases are fine. As section headings it's wild imo |
|
| ▲ | rogerrogerr an hour ago | parent | prev [-] |
| I think we’re talking about the obvious AI tells that apparently only some of us can see. Versus some of us look at five tells and say “nah, this is fine in isolation” over and over. |
