News for hackers. Stuff that matters.
Re:Bypass DeepSeek censorship by speaking in hex by B1FF_PSUVM on Saturday February 01, 2025 @08:08AM (#42898015)
> not as statistical machines, but geometric machines. When you train LLMs you are essentially moving concepts around in a very high dimensional space.

That's intriguing, and would make a good discussion topic in itself. Although I doubt the "we have the same thing in [various languages]" bit.

Re:Bypass DeepSeek censorship by speaking in hex by CSSer on Saturday February 01, 2025 @08:22AM (#42898095)
What do you mean, exactly, about the doubting part? I thought it was fairly well known that LLMs possess superior translation capabilities.
Re:Bypass DeepSeek censorship by speaking in hex by B1FF_PSUVM on Saturday February 01, 2025 @02:37PM (#42901405)
Sometimes you do not have the same concepts - life experiences are different.
Re:Bypass DeepSeek censorship by speaking in hex by Retric on Saturday February 01, 2025 @08:29AM (#42898137)
Mother/water/bed/food/etc easily translates into most (all?) languages. Obviously such concepts cross languages.

In this analogy they are objects in high dimensional space, but we can also translate concepts that don’t have a specific word associated with them. People everywhere have a way to refer to “corrupt cop” or “chess opening” and so forth.

Re:Bypass DeepSeek censorship by speaking in hex by quectophoton on Saturday February 01, 2025 @10:14AM (#42898931)
> Mother/water/bed/food/etc easily translates into most (all?) languages. Obviously such concepts cross languages.

See also: Swadesh List and its variations (https://en.wikipedia.org/wiki/Swadesh_list), an attempt to make a list of such basic and common concepts.

"Bed" and "food" don't seem to be in those lists though, but "sleep" and "eat" are.