When tested with a classic psychological assessment, advanced AI models experienced a total breakdown in focus. A new PNAS Nexus study suggests these systems lack the human-like executive control necessary to override automatic responses and maintain complex goals.
If you are not interested in how it completes the task then you are not an authority on how it works.
I’m academically interested, what I mean when I say I’m not interested is that I just don’t see the significance when we’re talking about if it’s capable of the task.
How are you able to understand it’s capability without understanding what tools it is capable of manipulating to effect?
You aren’t, and that’s exactly what I’m saying, it’s capable of doing these things with tools, therefore it’s capable of doing these things.
So why are you allergic to people talking about the quality of the tools in regards to capability?
I don’t know what you mean, I wasn’t the one who claimed they couldn’t do something they clearly can.
You are the one collapsing tool use into a binary when there are varying degrees of competency and hand holding.
I am not, you inaccurately said that the math olympiad was not bested by llm’s because they had a tool that told them if they were close but incorrect and can just try an infinite number of times. This is incorrect, they had a number of tries with python. This just isn’t a true statement. I think them besting it with use of python is equally significant and still counts as them besting it, and saying they can’t do math work is absurd.
It’s not “bested” by the LLM though, a mathematician used the LLM as a tool to disprove a conjecture. Subtract the mathematicians from the process and the LLM would not have successfully completed the task. It would be more accurate to say a mathematician with an LLM was able to best a mathematician who did not have an LLM. Which is cool, but we don’t need to pretend the LLM is not a tool but something that “understands” math like a mathematician