The chatbot excels at science, beating PhD scholars on a hard science test. But it might ‘hallucinate’ more than its predecessors.

I know people here are very skeptical of AI in general, and there is definitely a lot of hype, but I think the progress in the last decade has been incredible.

Here are some quotes

“In my field of quantum physics, it gives significantly more detailed and coherent responses” than did the company’s last model, GPT-4o, says Mario Krenn, leader of the Artificial Scientist Lab at the Max Planck Institute for the Science of Light in Erlangen, Germany.

Strikingly, o1 has become the first large language model to beat PhD-level scholars on the hardest series of questions — the ‘diamond’ set — in a test called the Graduate-Level Google-Proof Q&A Benchmark (GPQA)1. OpenAI says that its scholars scored just under 70% on GPQA Diamond, and o1 scored 78% overall, with a particularly high score of 93% in physics

OpenAI also tested o1 on a qualifying exam for the International Mathematics Olympiad. Its previous best model, GPT-4o, correctly solved only 13% of the problems, whereas o1 scored 83%.

Kyle Kabasares, a data scientist at the Bay Area Environmental Research Institute in Moffett Field, California, used o1 to replicate some coding from his PhD project that calculated the mass of black holes. “I was just in awe,” he says, noting that it took o1 about an hour to accomplish what took him many months.

Catherine Brownstein, a geneticist at Boston Children’s Hospital in Massachusetts, says the hospital is currently testing several AI systems, including o1-preview, for applications such as connecting the dots between patient characteristics and genes for rare diseases. She says o1 “is more accurate and gives options I didn’t think were possible from a chatbot”.

  • KobaCumTribute [she/her]@hexbear.netEnglish
    45·
    27 days ago

    All of their models have consistently done pretty good on any sort of standard test, and then performed horribly in real use. Which makes sense, because if they can train it specifically to make something that looks like the answers to that test it will probably be good at making the answers to that, but it’s still fundamentally just a language parser and predictor without knowledge or any sort of internal modeling.

    Their entire approach is just so fundamentally lazy and grifty, burning massive amounts of energy on what is fundamentally a dumbshit approach to building AI. It’s like trying to make a brain by just making the speech processing lobe bigger and bigger and expecting it’ll eventually get so good at talking that the things it says will be intrinsically right instead of only looking like text.