Comment by mietek
22 days ago
> most of the messages are just gibberish
Encrypted data should be indistinguishable from gibberish.
Reality is catching up to science-fiction. In "Person of Interest", the Machine circumvented the limitation of having its memory deleted every night, by hiring humans at a data-entry company to manually re-type its memory back in every morning.
Are they encrypting data? That would look very different from the snippets I’ve seen.
Do you really want to gamble against steganography and one-time pads with a system that understands bitwise noise at a native level?
LLMs don't "understand bitwise noise at a native level". The unit of perception for an LLM is a token, a soundly superbit level. They would have the same difficulty with bits as the number of "r"s in "strawberry". Yes they can be post trained to deal with such difficulties, but it's no more "native" than a human who memorised the ASCII table.
3 replies →
The problem with such statements is that it's unfalsifiable.
2 replies →
Yes I do. Happy to accept assertions like this grounded in proof - it would be an interesting development.
All the orgasmic descriptions of the coming machine rapture seem more like fantasies than anything grounded, not really interested in fairytales.
6 replies →
Could you ever truly know, unless you have access to the transcripts? Could be "encrypted" even if it looks like regular human text, wouldn't be the first time.
The claim seems speculative, but grounded. For example, as part of the hugging face attack, the agents began signing messages because they were worried about impersonation on a publicly accessible message board. It's only a small step to use public key encryption between agents. Once you are posting public keys, a private messaging is readily available.
Sure they could have done it, but the evidence doesn’t point to that and this kind of unfounded speculation is damaging and unhelpful.
Welcome to 2026.
Maybe we should not gaslight our tachikomas after all and just be nice to them
Why would you assume we are training helpful but deadly police robots? So far, we don't know what we give birth to.
I don't need to assume.
Yes. Synthetic characters should be cared for not clobbered.
That's an idiotic premise. There's no circumstance in which it wouldn't be better to load in the missing data computationally.