Rendered at 05:33:18 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
wavemode 6 hours ago [-]
This is a de-AI-izer, not a "humanizer". It removes AI tics, it doesn't add human voice.
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.
seanmcdirmid 1 hours ago [-]
Does it consider word rhythm in a sentence? When I revise what I write, I hear the words in my head and make sure they sound write together, and often across sentences. I wonder where that came from, and if AI can replicate it. Maybe it’s probabilistic?
totetsu 4 hours ago [-]
The biggest failing is that, when I write something, I have a theory of the world and the mind of the person or the people who might read it, and I adjust accordingly. Current text generation systems completely miss this point no matter how nice the writing can be made.
antonvs 3 hours ago [-]
It's not that simple.
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.
jpease 3 hours ago [-]
I find 79% to be the sweet spot.
bushido 6 hours ago [-]
Curious how this is different from simple english [0][1]. I've tested that one across multiple harnesses, and it works pretty well.
wow even just asking it for 80% of the way to ASD-STE100 makes a huge difference in readability. I'm experiencing way less brain fog trying to read opus.
datadrivenangel 7 hours ago [-]
ISO 24495-1 is the way for technical writing.
cadamsdotcom 8 hours ago [-]
Very cool, thanks for this! Looks super useful for all kinds of copy..
Am I crazy or does the skill itself look like slop, complete with disclaimers back to the user embedded into the skill file itself?
"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."
grey-area 6 hours ago [-]
Yes it absolutely is slop, full of AI tells. Why do we need all this ridiculous ceremony for a text file of instructions anyway?
If I want to control how it writes I just put a style_guide.md in the context.
_vertigo 4 hours ago [-]
Honest question: why does it matter if the skill is slop? It's designed for use by an LLM, I'm not planning on reading it.
z2 4 hours ago [-]
I'm totally fine with that, but I think there are still quality standards that if a bit higher, would let the skill at least be much smaller and thus less token-consuming. One place where I draw the line is when somebody, with minimal effort using an LLM, could have improved the quality of the LLM generated output. Also, I treat skills like programs and skim all external skills to make sure that they're not doing things they shouldn't be doing.
3 hours ago [-]
what 6 hours ago [-]
Why does a SKILL.md include “sources and credits”? The entire thing is pure slop.
bagacrap 2 hours ago [-]
> Karpathy talks about readability, not about sounding human. This skill adds that part, because the two methods cover each other's gaps.
I guess the author forgot to use his own skill.
bemtevi 6 hours ago [-]
Maybe instead of using this, one should just have some pride and learn to write properly, instead of relying on a machine for everything.
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.
[0] https://github.com/AminBlg/SimpleEnglish
[1] https://news.ycombinator.com/item?id=49114639
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.
I guess the author forgot to use his own skill.