←back to thread

Recent AI model progress feels mostly like bullshit

(www.lesswrong.com)
579 points paulpauper | 2 comments | 06 Apr 25 18:01 UTC | HN request time: 0.476s | source
Show context
aerhardt ◴[06 Apr 25 19:30 UTC] No.43604214[source]▶
My mom told me yesterday that Paul Newman had massive problems with alcohol. I was somewhat skeptical, so this morning I asked ChatGPT a very simple question:

"Is Paul Newman known for having had problems with alcohol?"

All of the models up to o3-mini-high told me he had no known problems. Here's o3-mini-high's response:

"Paul Newman is not widely known for having had problems with alcohol. While he portrayed characters who sometimes dealt with personal struggles on screen, his personal life and public image were more focused on his celebrated acting career, philanthropic work, and passion for auto racing rather than any issues with alcohol. There is no substantial or widely reported evidence in reputable biographies or interviews that indicates he struggled with alcohol abuse."

There is plenty of evidence online that he struggled a lot with alcohol, including testimony from his long-time wife Joanne Woodward.

I sent my mom the ChatGPT reply and in five minutes she found an authoritative source to back her argument [1].

I use ChatGPT for many tasks every day, but I couldn't fathom that it would get so wrong something so simple.

Lesson(s) learned... Including not doubting my mother's movie trivia knowledge.

[1] https://www.newyorker.com/magazine/2022/10/24/who-paul-newma...

replies(27): >>43604240 #>>43604254 #>>43604266 #>>43604352 #>>43604411 #>>43604434 #>>43604445 #>>43604447 #>>43604474 #>>43605109 #>>43605148 #>>43605609 #>>43605734 #>>43605773 #>>43605938 #>>43605941 #>>43606141 #>>43606176 #>>43606197 #>>43606455 #>>43606465 #>>43606551 #>>43606632 #>>43606774 #>>43606870 #>>43606938 #>>43607090 #
hn_throwaway_99 ◴[06 Apr 25 19:57 UTC] No.43604434[source]▶
So, in other words, are you saying that AI model progress is the real deal and is not bullshit?

That is, as you point out, "all of the models up to o3-mini-high" give an incorrect answer, while other comments say that OpenAIs later models give correct answers, with web citations. So it would seem to follow that "recent AI model progress" actually made a verifiable improvement in this case.

replies(1): >>43604458 #
1. saurik ◴[06 Apr 25 20:00 UTC] No.43604458[source]▶
I am pretty sure that they must have meant "up through", not "up to", as the answer from o3-mini-high is also wrong in a way which seems to fit the same description, no?
replies(1): >>43604505 #
2. hn_throwaway_99 ◴[06 Apr 25 20:03 UTC] No.43604505[source]▶
I tried with 4o and it gave me what I thought was a correct answer:

> Paul Newman was not publicly known for having major problems with alcohol in the way some other celebrities have been. However, he was open about enjoying drinking, particularly beer. He even co-founded a line of food products (Newman’s Own) where profits go to charity, and he once joked that he consumed a lot of the product himself — including beer when it was briefly offered.

> In his later years, Newman did reflect on how he had changed from being more of a heavy drinker in his youth, particularly during his time in the Navy and early acting career, to moderating his habits. But there’s no strong public record of alcohol abuse or addiction problems that significantly affected his career or personal life.

> So while he liked to drink and sometimes joked about it, Paul Newman isn't generally considered someone who had problems with alcohol in the serious sense.

As other's have noted, LLMs are much more likely to be cautious in providing information that could be construed as libel. While Paul Newman may have been an alcoholic, I couldn't find any articles about it being "public" in the same way as others, e.g. with admitted rehab stays.