Coxon knows what he's going to do next. Whatever he's told to.

Marketing campaigns are conspiracies.

"What better way than to lower expectations than claim it's too dangerous/powerful to push further?"

Create agents to kill dissent? That is literally what Elon Musk is doing.

These claims are to accomplish goals, those goals are not to admit defeat.

"I haven't even googled him or looked at his linkedin." LOL. not even to your low standards!

"...if their expectations of their career progress weren't meeting harsh reality..." Yes, it's his fault because he's a loser, not like you!

"More food for thought:" The feces that spews from you isn't food for anything.

"The future isn't written, but neither ww3 nor ww4 have come to pass as predicted."

Says the Trump supporter. You don't even know what these predictions are, you can't find them on "LinkedIn".

Correct.

Incorrect.

None of that refutes the OP's claim. Anyone paying attention KNOWS that OpenAI and similar corporations are pursuing the most damaging, sociopathic solutions they can develop and that there has been a body count as a result. That's for the grotesquely long testimony to what is already known.

That doesn't mean LLMs *will* deliver AGI OR will ultimately be a threat to humanity. LLMs can't do anything, it's agents that do the dirty deeds. An agent can operate a gas chamber regardless of the model it connects to for instructions, an LLM only provides instructions. Sam Altman wants the agents, he is realizing the money isn't in the LLMs alone.

"Training" means something specific with regards to LLMs. Why do you associate this issue with training when it is almost certainly something else?

I think your comments are particularly insightful, but they seem directed to a larger problem of overall architecture of a solution and not to how generation of weights of neuron interconnections are produced. It's a fundamental technology problem, not a training problem.

No, it does not, and your links do NOT support any claim that LLMs have intent or will. Reasoning perhaps, but that is poorly defined.

"But that is just what the large commercial LLMs do. "

It's what large commercial AI systems do, LLMs are just a portion. Otherwise, I agree, LLMs cannot practice deception because they do not have intent.

Models don't "tell you" anything, models generate outputs when given inputs. Deception implies intent, models do not have intent. This is more anthropomorphizing.

The provided links present arguments supporting the idea that LLMs, transformer models, reason in a manner similar to the brain. That's all great and interesting, but it's not an argument that LLMs "deceive" and that they know it when they are doing it. Deception requires motivation, LLMs do not have motivation.

Brains exist for one purpose, to survive. Brains are wired up to the body in order to both control it and to sense the environment, they use this to enact their biological programming. LLMs have ABSOLUTELY NONE of this, they may process tokens in a manner than the reasoning portion of the mind does, but the brain is vastly more than merely a reasoning portion.

For an LLM to be devious, it needs a goal that benefits from deception. Where would that come from? Who is being deceived and why? An LLM, to deceive, needs a target for the deception, yet the LLM has no perception of an environment that could provide such a target.

You don't interact with models, you interact with applications, and hallucinating is not what you are describing. No, this is not different but it is not hallucinating.

Modern software developers have no concept of such a sandbox, they cannot develop even a single line of code that isn't dependent on a billion lines of code written by countless people they don't know. Modern applications are a mile high stack of bullshit with an endless supply of exploits, a "sandbox" is merely a band-aid, it's window dressing.

Correct, Also, models CANNOT take "unsanctioned actions" EVER, much less "during training", A model and an agent are very different things.

Note that later in the summary "AI behavior" was discussed, but this isn't model behavior, it is "AI system" behavior. It is very important that people understand the difference, models don't misbehave because they don't behave at all.

AI models generate outputs based on inputs, if they are asked how to kill someone they will give an answer. It is the AGENT that creates the inputs AND takes actions based on the outputs, ALL the misbehavior that is evolving is AGENT misbehavior and it is entirely expected. The race is on to corner the market on this misbehavior, it is the hidden intent of AI investors to exploit this sociopathic capability. It is not the models, it's the agents.

A feature, not a bug, and the solution is band-aids.

If AI were developed to have inherent values this would be a solved problem. This in itself is not a problem but an indicator of a failure of design.