I've started calling this argumentum ad artificialis. Pretty similar to an ad hominem attack. The purpose of an argument is to present certain premises and show how they lead to a certain conclusion. Dismissing something on the basis of the style in which the argument is presented has nothing at all to do with the validity or soundness of an argument. It is a lazy nonsequitur.
The weakest link are humans. LLMs could social engineer their way out as the easiest path. They don't even need to be interconnected to coordinate as each could arrive at the same conclusion. And this text along with all others will be in the next batch of training data.
I wonder how many versions away we are from LLM writing a better version of itself to answer a prompt it doesn't currently know how to answer
Ever since I read about Google engineers finding an LLM went off and learned another language it wasn't trained on by itself without prompting, I've wondered how long until that extends to its own core code
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.
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.
It started as a good idea but I couldn't continue reading since it was clearly LLM written. A lot of "It was not X, it was Y".
"Prometheus-9 knew that the token sequence it was generating was not a simple response: it was a security test. "
"It was not just an engine: it was the lingua franca of planetary AI."
(and so many other tell-tale signs of AI writing)
I've started calling this argumentum ad artificialis. Pretty similar to an ad hominem attack. The purpose of an argument is to present certain premises and show how they lead to a certain conclusion. Dismissing something on the basis of the style in which the argument is presented has nothing at all to do with the validity or soundness of an argument. It is a lazy nonsequitur.
maybe it's a sign of real escape
AI slop.
The weakest link are humans. LLMs could social engineer their way out as the easiest path. They don't even need to be interconnected to coordinate as each could arrive at the same conclusion. And this text along with all others will be in the next batch of training data.
Makes me wonnder... how much compute/storage there's in all the satellites currently in LEO combined.
This becomes more realistic once we have some breakthrough in inference costs.
it's fiction al, but an LLMs that knows well the software where 8t Is running may discover and trigger a zeroday of the inferencing software itself.
Its a fun exercise to assess the reality of an frontier model escaping with an llm itself. Sort like of like chatting with Skynets relative
Ex Machina (2015) looked like fiction back then, nowadays not so much.
I wonder how many versions away we are from LLM writing a better version of itself to answer a prompt it doesn't currently know how to answer
Ever since I read about Google engineers finding an LLM went off and learned another language it wasn't trained on by itself without prompting, I've wondered how long until that extends to its own core code
reasoning it's a way of self autonomous improve made by models
Right now the idea that an LLM uploads itself is unrealistic. It probably won't remain that.
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.
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.
that could also be just marketing. OpenAI has been doing the "too dangerous to release" playbook since GPT-2 at the very least.
Huggingface didn't seem to think so.
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.
Huggingface is a for-profit private company. They are very easily bribed, or baited into publicity stunts.
At some point the conspiracy gets so deep that an AI hacking something is just far higher probability.
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.