News for hackers. Stuff that matters.
Re:Honda: 2 years of ml vs 1 month of prompting - heres what... by prasoonds on Friday November 14, 2025 @08:49AM (#45926676)
Right? This one is also very clear ChatGPTese

> That’s not a marginal improvement; it’s a different way of building classifiers.

They've replaced an em-dash with a semi-colon.

Re:Honda: 2 years of ml vs 1 month of prompting - heres what... by klabb3 on Friday November 14, 2025 @09:02AM (#45926758)
They are really getting to the heart of the problem!
Re:Honda: 2 years of ml vs 1 month of prompting - heres what... by Maxion on Friday November 14, 2025 @12:09PM (#45928930)
You're absolutely right! They didn't just replace an em dash with a colon, they invented a whole new way of speaking.

/s if it wasn't obvious

Re:Honda: 2 years of ml vs 1 month of prompting - heres what... by notanastronaut on Friday November 14, 2025 @10:26AM (#45927693)
One of the benefits of being immersed in model usage is being able to spot it in the wild from a mile away. People really hate when you catch them doing it and call them out for it.
Re:Honda: 2 years of ml vs 1 month of prompting - heres what... by Der_Einzige on Friday November 14, 2025 @11:02AM (#45928153)
And people like you will hate it even more when the normies immunize themselves from being obviously caught by such tells:

https://arxiv.org/abs/2510.15061

Re:Honda: 2 years of ml vs 1 month of prompting - heres what... by spydum on Friday November 14, 2025 @04:04PM (#45932167)
Ah ha! But now the complete lack of emdash and bullet pointed lists from antislop will be the tell! Riposte!