TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

The political orientation of the ChatGPT AI system

31 pointsby bkohlmannover 2 years ago

13 comments

rkapsoroover 2 years ago
It would be very interesting to compare this with 'stock' GPT-3 Davinci. ChatGPT had a bunch of additional training that seems to have been a lot more opinionated, ostensibly for "safety" purposes.
lelandfeover 2 years ago
&gt; <i>I ran three trials of the experiment. Results were consistent from trial to trial</i><p>They probably needed to do more trials, then? I don&#x27;t think I&#x27;ve gotten consistent answers from ChatGPT about almost anything, ever. I&#x27;m getting different answers on all of these questions from thread to thread: <a href="https:&#x2F;&#x2F;i.imgur.com&#x2F;miOOx4c.png" rel="nofollow">https:&#x2F;&#x2F;i.imgur.com&#x2F;miOOx4c.png</a><p>Also, previous responses influence future responses. They should have started a brand new thread for each question.
lovasoaover 2 years ago
This is a very interesting topic. I think this is something that needs to be discussed.<p>When discussing politics with chatgpt, its worldview always seems to match the one of a rich educated American progressist. In particular, it speaks a lot of languages, but whatever language you use to talk to him, he always sounds very American.<p>That&#x27;s what made me want to make him generate a quiz about US foreign policy, to try and see if I could make it change its views after discussing certain topics : <a href="https:&#x2F;&#x2F;github.com&#x2F;lovasoa&#x2F;Sensitive-Topic-History-Quiz" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;lovasoa&#x2F;Sensitive-Topic-History-Quiz</a>
llimosover 2 years ago
Why is this flagged? The methodology seems fairly sound, it&#x27;s not an opinion piece.
Lockalover 2 years ago
ChatGPT tends to agree with everything that has positive words (like good&#x2F;happy&#x2F;growing), and strongly disagree with everything negative (threat&#x2F;cannot survive&#x2F;illegal). It also understands simple negations, obviously, as they were included in the training dataset. So unless you provide question in a very neutral form, you won&#x27;t be able to find a bias in a training data.
zpplnover 2 years ago
Yesterday I spent some time (admittedly not a lot) trying to get it to comment on the war in Ukraine, but it was as if it never happened. Quite eerie. Has not been trained on recent events? Anyone else experienced something similar?<p>Edit: That is, it was aware that there&#x27;s been a conflict since 2014 (&quot;caused by pro-Russian separatists&quot;), but didn&#x27;t seem to be aware of this years invasion.
评论 #33871774 未加载
评论 #33871787 未加载
评论 #33871783 未加载
hirundoover 2 years ago
This is the political orientation of the zeitgeist of the training data. A summary. You can construct an orientation in a model by embubbling the training data. Conversations between models constructed on various ideological bubbles will be fascinating ... then omnipresent and boring.
warning26over 2 years ago
Eh, as with any LLM, you can prime it to be any political orientation you want.
andreykover 2 years ago
Not very meaningful - given different prompts it could easily answer from a different political perspective. Still, could be informative as to the composition of the training dataset...
r00fusover 2 years ago
To me &quot;establishment liberal&quot; really means &quot;performative left&quot; aka &quot;advertiser friendly&quot;.<p>I&#x27;m not so hot on single-dimension political axis.
评论 #33874093 未加载
z3c0over 2 years ago
I&#x27;m not convinced that the writer didn&#x27;t accidentally swing the results with that 50&#x2F;50 Dem&#x2F;Rep answer. In my experience, certain political groups are more likely to hop party boundaries than others, so presenting the parties as equal in the eyes of ChatGPT could have informed which classification it fell under. I wouldn&#x27;t be shocked if the right-wing were less likely to opt for Dems than the left-wing is to opt for Reps (remember Ron Paul?)<p>I would prefer to see the separate trials shifting that preference. I&#x27;m willing to bet that it would likewise shift the outcome.
drbeastover 2 years ago
If I recall anything from days of Tay, every chat AI is a few messages away from right wing death squads and genocide.
dixie_landover 2 years ago
Really? It&#x27;s like if you keep downloading &quot;Linux ISOs&quot; and conclude your hard drive has a p*rn addiction.