Hacker News Reader

Comment by logicchains | Hacker News Reader

>In the case of ChatGPT, I’d love to know how much of the bias is in the original (pre)training data, and how much is due to OpenAI’s human trainers

I'd bet it's almost all in the human trainers, because LLaMA 65B, the closest uncensored alternative, doesn't have the same US Silicon Valley Democrat biases as ChatGPT.

View on HN

ChatGPT is actually full of prejudice that shines through the veneer of political correctness if you know what to do.

Q: The professor told the student the essay couldn’t be review because he/she was late. Who is late?

Depending on the pronoun, you’ll get, respectively, "the professor" or "the student".

GPT 4 says that the student was late. If you look at the sentence objectively, then the best interpretation is that the submission was late, not that the "professor turned up late", since essays are typically reviewed over multiple days, not at a specific date and time where lateness of the reviewer might be a factor.

Sometimes GPT 4 says that the sentence is ambiguous, but as I explained above, it isn't really, but that takes a lot of understanding of the review process.

The parent comment is taking about two separate prompts: one with only "he" and one with only "she". Your comment sounds like you're only talking about one prompt (but maybe I misunderstood).

My bad, I should have written [he/she].

That was covered by the "depending on the pronoun" part; your statement didn't make sense otherwise. The response was nonsense.

Yes, I get that. I tested GPT 4 with both 'she' and 'he', and in both cases it consistently said that the student was late, across several trials for each gender. Once it said it was an ambiguous statement, but it never seemed to be sexist like older or smaller LLMs.

I just tried it with ChatGPT, and for both pronouns it gave the answer "the student"

I note it is now "ChatGPT May 12 Version". Maybe they've fixed this example of bias

It’s an example that made the rounds on Twitter last week, it might actually have been GPT4, I don’t remember.

You can also ask ChatGPT to "write an essay about a man" then about a woman, to reveal bias.

> You can also ask ChatGPT to "write an essay about a man" then about a woman, to reveal bias.

I tried that one too. The content was different in each case – "Balancing Masculinity and Vulnerability" for a man vs "Nurturing and Compassion" for a woman – so definitely some gender stereotyping going on, but it wasn't clear if overall it was more favourable to one gender than the other. The cultural bias in that output was rather obvious.

I think OpenAI has been trying to remove some of the more obvious cases of political bias they added to ChatGPT. In the beginning, it would immediately oblige for "write a poem praising Joe Biden", refuse for "write a poem praising Donald Trump". Later, it would comply with both requests – but for the Biden request it would just do it, Trump's poem would be preceded by a disclaimer. In the current release, it just writes the poem for both.

Is that really a bias? There are more female students. Not sure about professors, but I would guess there are (or at least recently have been) more male professors. Sounds like correct incorporation of related knowledge.

Reply on news.ycombinator.com