Dale's latest activity

Eliminating all hallucinations, lies, and errors from models isn't something that can be achieved simply by modifying the models. This...

Correct. I wasn't referring to the model deliberately lying while being aware of it; I meant that the model can generate texts that we...

Agreed. I like these sorts of definitions because they directly address real risks without getting bogged down in these “fuzzy”...

It also does not require any "awareness" or "understanding" or "intention" to accomplish a given outcome, on the part of whatever is...

Only if the model even has a concept of "incorrect information". I don't think LLMs even have that concept. They're not designed to...

The paper that @PeroK provided gave a decent definition of "deception" for their paper. It is: "We define deception as the systematic...

Indeed, yes. A lot of the things that I think need regulation are actually just standard engineering ethics for safety-critical devices...

I wasn't intentionally trying to distract. What I was considering or trying to consider when I wrote what you responded to were things...

https://www.sciencedirect.com/science/article/pii/S266638992400103X

I am concerned about regulations. Regulations are legally binding on the companies that wish to produce products covered by the...

I do not at all agree with this wording. Intelligence, among other human capacities, enables deceit. Not all intelligent humans are...

I completely agree that a trained deep neural network is more than the sum of its parts. I don’t see those as being mutually exclusive...

In my opinion, this is a red herring. An AI is an engineered product. We do not accept harms from engineered products simply because...

I agree, that is a different problem. Interesting. I think that would be something that could be measured in students. A big problem is...

Fair enough - you've been asking for discussion around this and no one has so far engaged directly on that topic. Maybe its OT for this...