114 points | 12d ago | Discuss on Hacker News | Back to Radar
Wonder if it also defeats text watermarking.
"A warning about the original post. It came with an overview graphic of STE. A later fact check found errors in that graphic. For example, "approximately" is an approved word, and the dictionary has no entry for "in order to". This skill follows the rules of Issue 9, not the graphic."
If I want to control how it writes I just put a style_guide.md in the context.
The more slop you have in your context the sloppier the text you get out will be.
This tool appears primarily designed to produce text that's clearer and more concise, not to produce text that fools someone into thinking a human wrote it.
Functionally speaking, i.e. talking about observable output and not making any claims about LLM "mental states", there are plenty of examples where LLMs demonstrate good theories of the world and theory of mind. They can even exhibit, again from a functional perspective, emotional intelligence.
However, they need input to tell them what the world in question is like and what the minds are like. Otherwise, they're just operating from an enormous amount of often-conflicting pretrained data.
You're more likely to see good results in this area when interacting directly with one, so that it has some history of the interlocutor's writing, or when doing something like coding where "the world" is something like a codebase, along with the pretrained information it has about that kind of code.
Code is a good example, because the results they give in that context would not be possible without some equivalent of a theory of the subject. This applies to pretty much any kind of reasoning that models do - in math, logic, physics etc.
When writing for a more general audience, models lack this kind of information, so you would have to supply it in some form.
The other issue is that whatever theories are implied by their writing are not necessary stable, because of issues like context size limitations, compaction, selective attention, etc. Nevertheless, it's a big oversimplification to say that they don't possess the functional equivalent of such theories.
I guess the author forgot to use his own skill.
Even that sentence sounds AI to me. Humans don't write like that, with "the skill removes" at the end of a sentence.
And you don't seem to mind the influence on education. Odd.
Although some of the comments here have complained about the idea, I think they're missing the point. Although the skill and similar rules can be used to hide the fact you're using AI, it can also be used to make interacting with AI easier, i.e. when you're in a long coding session it can be quite daunting to be presented with so many questions and exhausting to look for the important decisions buried in an overwhelming amount of text. For those of us who are using AI to code, which is almost everyone now, this approach is likely to be very useful to reduce the cognitive overload.
Comments are loaded live from Hacker News and are not stored by Mid or Real.