Hacker News Reader

Comment by ISL | Hacker News Reader

Is a layman's interpretation of this to state: LLMs tend to perform like aggregated humanity, but any given human will differ. Since all the volume of a high-dimensional sphere is at the edge, almost nobody is like the mean, so the false-positive-rate is low?

It's a clever plan, until the LLMs do some adversarial training....

View on HN

>It's a clever plan, until the LLMs do some adversarial training....

it's an unwinnable war.

It depends on what you're trying to achieve. For a spam filter that downranks low-effort noise (or equivalently, ranks more interesting stuff higher), it might be useful enough?

This is a super clear explanation!

Perhaps this measurement approximates a human reaction to chatGPT: 'This writing is distinctly indistinct.'

Made me think of how the bomber planes pilot seats were designed to the average human, which meant it fit no human.

Sounds like the bed of Procrustes: https://en.wikipedia.org/wiki/Procrustes#Mythology

Yeah it kind of sucks for people who don't like these systems that efforts to resist them are essentially the same as using GANs to train them.

https://www.smithsonianmag.com/history/what-the-luddites-rea...

> They did not invent a machine to destroy technology, but they knew how to use one. In Yorkshire, they attacked frames with massive sledgehammers they called “Great Enoch,” after a local blacksmith who had manufactured both the hammers and many of the machines they intended to destroy. “Enoch made them,” they declared, “Enoch shall break them.”

... And another reference for the phrase...

https://www.nigeltyas.co.uk/nigel-tyas-news/post/enoch-the-p...

> And here’s the funny thing. The weapons they reached for to wield and smash the machines were sledge hammers made by ... the Taylor brothers of Marsden. This irony was not lost on the Luddites and as they swung ‘Enoch’s hammers’ to damage his hated machines they cried: “Enoch made them, and Enoch shall break them”.

Fighting fire with fire.

Yes, and do we even need to wait? You could ask GPT-4 right now to write something imperfect.

Maybe optimizing for “an amount of imperfections, variability, and subtle but tell-tale clues as to convince an examiner that the writer is human and not a language model.”?

If that’s not enough it could also be asked to read the paper itself and suggest additional countermeasures based on a technical review.

Good summary. I wonder if the "perform like aggregated humanity" behavior comes from using greedy decoding. If you actually sample according to the token probs, it seems like you should still end up "on the edge".

This is very succinct, but can someone reduce more to explain it like i'm five level.

https://readingbyeugene.com/2016/05/15/there-is-no-such-thin...

Are You Normal? Hint: No

https://allendowney.github.io/ProbablyOverthinkingIt/gaussia...

Reply on news.ycombinator.com