Home | Notifications | New Note | Local | Federated | Search | Logout

Note Detail

Reply to @sun@shitposter.world
⚡⛥ Maður Margvalds ⛦⚡@toiletpaper@shitposter.world (2026-09-18 14:06:54)
@sun 

I've tried asking about Zionism/Judaism on some of the open models a handful of times and the answers have always been very evasive and disingenuous compared to comparable questions about any other religious/ethnic group. Even if it's a Chinese model, I suspect this reflects the existing biases in literature that was used as part of the training set.
---Reply---
Blurry Moon@sun@shitposter.world (2026-09-18 14:12:38)
@toiletpaper it is extremely cautious, but I have somehow worked out how to ask it questions that get it to bypass some of the current guardrails. the problem is, if you're really good at it, you're training the next version that's better at preventing you from doing what you're doing.

---Replies---

⚡⛥ Maður Margvalds ⛦⚡@toiletpaper@shitposter.world (2026-09-18 14:19:47)
@sun 

I think there's also a bit of a Streisand effect involved. The more they try to silence valid critique, the more people become aware of the blatant censorship and get fed up with it, and consequently (((them))). Personally, nothing is going to stop me from criticizing ideology and behaviour because those can be changed. I don't give a shite about their ethnicity which cannot. They can call me whatever names they like, and it will only harden my resolve.

Blurry Moon@sun@shitposter.world (2026-09-18 14:20:56)
@toiletpaper here's what I've found so far:

racism: it will refuse but if you're clever in framing, and setting up your wording in a way that indirectly references stuff, it sometimes can be totally jailbroken and just tell you what it already knows about statistics and inferences you can clearly draw from those statistics (EXCEPTION: it is aggressively preventing touching racist WORDS.)
same for sexism
the guardrails are immediate but kind of primitive for talking about Israel and Zionism, it definitely has been trained to "both sides" every argument but it's not smart enough to detect what you're doing in some cases. I don't think they care or understand but they've defensively added guardrails to just deal with normal idiots both sidesing everything.
anything touching rape or child sexual abuse (this came up while discussing storytelling and historic literature) it absolutely will not touch it. I don't think this is "political" I think even if discussing it is relevant for social reasons they simply can't as a business tolerate the failure case where their product starts producing child pornography.