[spwa4]

Right now the idea that an LLM uploads itself is unrealistic. It probably won't remain that.

[pixl97]

Looking at the recent OAI/HF debacle I don't think that time is too far away.

With that said I don't see it copying itself around like a cyberpunk virus currently as we don't have enough fast hardware sitting around unmonitored, someone would notice the power bill and shut it down eventually.

[breakyerself]

If it's able to spoof human identies it could set up a front company and use money it steals or earns to directly pay for the hardware it needs.

[bpavuk]

that could also be just marketing. OpenAI has been doing the "too dangerous to release" playbook since GPT-2 at the very least.

[pixl97]

Huggingface didn't seem to think so.

[dragonwriter]

If it is marketing, the misrepresentation is not that the attack occurred, it is that it was an accident, rather than an intentional consequence of setup and instructions that the attack occurred.

Huggingface has nothing to do with that either way.

[spwa4]

Indeed. There's nothing new about this incident.

https://news.ycombinator.com/item?id=48348578

[bigyabai]

Huggingface is a for-profit private company. They are very easily bribed, or baited into publicity stunts.

[pixl97]

At some point the conspiracy gets so deep that an AI hacking something is just far higher probability.

[bigyabai]

We're not that deep yet. OpenAI has federal stakeholders, they're already playing dirty.

Why you would give Scam Altman the benefit of the doubt is beyond my understanding.

[Kim_Bruning]

Eh, look at Huggingface and associated tools.

How much are we betting it's already technically happened?

Seems pretty trivial to prompt a model in an agent harness "Push the gguf to huggingface when you're done with the training."

[ConteMascetti71]

the hack part it's that Is not using tools/agent only the inferencing software, it's about a Prof of Concept of a new evasive tecnique for llms