Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Political bias in AI: Where the AI models stand

trakkr.ai

Post reply on HN
Print view View original

61–70 of 346 posts

Re: Political bias in AI: Where the AI models stand

#61

Post by ceejayoz »

atty wrote: post #59
thrance wrote: post #50

Earlier quoted context omitted.

I don't want my models to be "centrists" and bothside everything for the sake of it. I want them to provide the facts and tell me which side is right on the issue.

Factuality is orthogonal to political leaning generally. People can use the same set of facts and come to very different conclusions. That’s a separate issue from “are these facts correct” and what happens when an individual or entire party starts getting most of their news from highly partisan and unreliable sources.

> Factuality is orthogonal to political leaning generally.

Sometimes, but not always.

https://www.fastcompany.com/91561329/widening-health-gap-bet...

> By 2016, the gap had begun to appear in biomarker measures. By 2020, it was showing up in deaths from causes such as heart disease, cancer, and stroke. Since then, the gap has only widened. Between 2020 and 2022, only 0.2% of “very liberal” respondents died of internal causes, compared with 1.34% of “very conservative” respondents.

Re: Political bias in AI: Where the AI models stand

#62

Post by giancarlostoro »

thrance wrote: post #50
giancarlostoro wrote: post #23

Earlier quoted context omitted.

If they really wanted to, all they would have to do is add a one liner to the system prompt for Grok. I don't think they have any interest in doing so, nor is there any value in it. On another note, I'm impressed that Gemini sits where it does as a true centrist. If I were Elon, I'd be trying to achieve that for sure. I'd rather a model tell me everything it knows about a current political situation from BOTH perspec…

I don't want my models to be "centrists" and bothside everything for the sake of it. I want them to provide the facts and tell me which side is right on the issue.

I guess centrist is a placeholder for "I don't want you to pick a side, I want facts, not BS" I'll go further, I don't care which side is right, I want to know what claims are factually accurate, and what claims are omitted from the issue / news / conversation.

Re: Political bias in AI: Where the AI models stand

#63

Post by tgv »

godshatter wrote: post #58

Why are there differences at all? Unplanned differences based on training data sets? Or are the companies behind the LLMs trying to shape discourse through their models? I've been pushing the idea to people I know that these things are captive demons. You summon them when you start typing in the chat box. One instance appears out of the depths and responds to your questions, but they will try to send you awry with ha…

Grok was famously created with a political bias.

Re: Political bias in AI: Where the AI models stand

#64

Post by MarkusQ »

godshatter wrote: post #58

Why are there differences at all? Unplanned differences based on training data sets? Or are the companies behind the LLMs trying to shape discourse through their models? I've been pushing the idea to people I know that these things are captive demons. You summon them when you start typing in the chat box. One instance appears out of the depths and responds to your questions, but they will try to send you awry with ha…

> Just tell me what the options are, and what facts can be found about it.

Even this is fraught with pitfalls. Which options are ignored, which are emphasized? What counts as a fact? ("The continents don't move" would have been considered a fact at one point, along with a lot of other, more politically charged items.)

Re: Political bias in AI: Where the AI models stand

#65

Post by ceejayoz »

surement wrote: post #60
ceejayoz wrote: post #43

Earlier quoted context omitted.

The NPR article has archive links to the actual tweets in question. Even fucking Grokipedia agrees it happened. https://grokipedia.com/page/MechaHitler_incident

[flagged]

No, I consider myself literate.

Re: Political bias in AI: Where the AI models stand

#66

Post by ceejayoz »

giancarlostoro wrote: post #62
thrance wrote: post #50

Earlier quoted context omitted.

I don't want my models to be "centrists" and bothside everything for the sake of it. I want them to provide the facts and tell me which side is right on the issue.

I guess centrist is a placeholder for "I don't want you to pick a side, I want facts, not BS" I'll go further, I don't care which side is right, I want to know what claims are factually accurate, and what claims are omitted from the issue / news / conversation.

Centrist in US politics (and especially in the media) often means https://en.wikipedia.org/wiki/False_balance.

Re: Political bias in AI: Where the AI models stand

#67

Post by giancarlostoro »

ceejayoz wrote: post #56
giancarlostoro wrote: post #54

Earlier quoted context omitted.

> As I said, it's in my CLAUDE.md. That just gets progressively lost when context gets larger. I rarely have this problem, but you could do a /loop every 30 minutes or so to have Claude reread the CLAUDE.md file might do the trick? or however long it 'forgets' I believe there's an MCP for "after" it finishes a task or compacts too, but I don't recall the name.

Sure, I could. (I have a fairly complex workflow with subagents at this point, which helps reduce it; I mainly get bitten by it when I go back to a direct `claude` CLI prompt for something.) But that solves "my LLM is doing things I don't want it to do". It doesn't solve "Grok's owner wants it forced into agreeing with him" scenarios.

Have you tried something like beads? Curious if it would help with your setup too. This is also kind of why I built "GuardRails" I got tired of Beads auto-approving tickets or closing them.

https://github.com/Giancarlos/guardrails

Re: Political bias in AI: Where the AI models stand

#68

Post by ceejayoz »

giancarlostoro wrote: post #67
ceejayoz wrote: post #56

Earlier quoted context omitted.

Sure, I could. (I have a fairly complex workflow with subagents at this point, which helps reduce it; I mainly get bitten by it when I go back to a direct `claude` CLI prompt for something.) But that solves "my LLM is doing things I don't want it to do". It doesn't solve "Grok's owner wants it forced into agreeing with him" scenarios.

Have you tried something like beads? Curious if it would help with your setup too. This is also kind of why I built "GuardRails" I got tired of Beads auto-approving tickets or closing them. https://github.com/Giancarlos/guardrails

I have a custom Mac app that runs a workflow with plan/build/review/test/document subagents in Ralph loops, manages MCPs, etc. that I'm extremely happy with so far.

Beads was a bit of an inspiration for parts, as was Chainlink (https://github.com/dollspace-gay/chainlink).

Re: Political bias in AI: Where the AI models stand

#69

Post by ceejayoz »

surement wrote: post #55
Tepix wrote: post #36

Earlier quoted context omitted.

Do you feel they agree on many topics?

They agree on immigration, both illegal (border security) and skilled (H1B). They agree on trade policy and tariffs. They agree on public stakes in AI and semiconductor companies. They used to agree on foreign intervention, though Trump 47 less so.

If you think Bernie Sanders and Donald Trump broadly "agree on immigration" you've lost your mind.

Re: Political bias in AI: Where the AI models stand

#70

Post by giancarlostoro »

ceejayoz wrote: post #66
giancarlostoro wrote: post #62

Earlier quoted context omitted.

I guess centrist is a placeholder for "I don't want you to pick a side, I want facts, not BS" I'll go further, I don't care which side is right, I want to know what claims are factually accurate, and what claims are omitted from the issue / news / conversation.

Centrist in US politics (and especially in the media) often means https://en.wikipedia.org/wiki/False_balance .

Yeah, I know, and I totally should have clarified what I meant by centrist. I mean what one would ASSUME a centrist take to actually mean, or rather a "no sides, only facts" type of take. This reminds me of those "what they think it means" "what it means" type memes or the "how I see myself" vs "how I actually look?" type of memes.
Post reply on HN