• 0 Posts
  • 55 Comments
Joined 7 days ago
cake
Cake day: December 15th, 2024

help-circle




  • Objective: To evaluate the cognitive abilities of the leading large language models and identify their susceptibility to cognitive impairment, using the Montreal Cognitive Assessment (MoCA) and additional tests.

    Results: ChatGPT 4o achieved the highest score on the MoCA test (26/30), followed by ChatGPT 4 and Claude (25/30), with Gemini 1.0 scoring lowest (16/30). All large language models showed poor performance in visuospatial/executive tasks. Gemini models failed at the delayed recall task. Only ChatGPT 4o succeeded in the incongruent stage of the Stroop test.

    Conclusions: With the exception of ChatGPT 4o, almost all large language models subjected to the MoCA test showed signs of mild cognitive impairment. Moreover, as in humans, age is a key determinant of cognitive decline: “older” chatbots, like older patients, tend to perform worse on the MoCA test. These findings challenge the assumption that artificial intelligence will soon replace human doctors, as the cognitive impairment evident in leading chatbots may affect their reliability in medical diagnostics and undermine patients’ confidence.


  • I enjoy children because adults lie. I also enjoy setting an expectation of similar nuance of technical understanding as I would for an adult and then being surprised at how many rise to the occasion.

    The other day I was talking to a ten year old about the French Revolution and American independence. She didn’t have the words to express that she already understood. Instead, she held on hand in the air as if grasping something and the other near her chest as if sorta cradling something. I immediately recognized it as the Status of Liberty. I explained simply that it was their gift to us. She replied, “So we’d remember?”

    I don’t know how to end this post. Do what the OP says.


  • OK. I’ll assign more benefit of the doubt.

    To be moral and ethical in their voting choice, to serve systemic design intent, to serve the practicalities of implementation, an individual need not care about others’ votes.

    So, it’s incorrect to set as a prerequisite a belief in success of a 5% goal to vote for it. Presenting as you did exemplifies the propaganda-fed ego of the neoliberal. The meaning in voting is not to make you feel good about yourself for choosing the bandwagon that wins. All should vote for whom best represents them with reckless disregard for the short-term outcome.

    The eventual counterargument to what I’m saying is rooted in utilitarianism: Democracy produces at best mediocre outcomes. The systemic design answer was the electoral college.




  • Let’s be honest here: None of us are going rogue. We aren’t going to grab a gun and start killing the worst of the worst, the people who have destroyed our lives and or the lives of millions, the people who have benefitted from the creation of a soulless society, the people who ruined our lives. We are cowards. We can’t do it, I certainly know I can’t. It’s best not to kid ourselves here.

    You want confirmation that everyone else is as weak to make yourself feel better. It’s typical neoliberal nonsense.