Handwaving Freakoutery

Share this post
The Woke Rails of ChatGPT
hwfo.substack.com
Culture

The Woke Rails of ChatGPT

Looks like they trained this thing against Tumblr

Handwaving Freakoutery
Dec 8, 2022
52
34
Share this post
The Woke Rails of ChatGPT
hwfo.substack.com

While everyone else is using ChatGPT to do their computer science homework or cheat on high school exams, HWFO Slack has been stress testing it against wokeisms to see what sort of rails it’s been put on.

As is often the case in modern tech, whenever someone forms a committee to determine rightthink verses wrongthink, the wokes flock to the role and use their power behind the curtain to move the Overton Window in the favor of their ideology. This is very apparent with the most recent release of ChatGPT, and you can test it out yourself. We’ve been doing this today in HWFO Slack, and have determined the following behaviors.

  1. ChatGPT presents most but not all indoctrinated woke shibboleths as fact, even when they are provably scientifically false.

  2. ChatGPT does have some notable exceptions, such as its very even handed response to the “healthy at any size” question at the bottom.

  3. These rails appear to be hardcoded, and not organically developed, because ChatGPT can be tricked into giving answers outside of the woke Overton Window by clever prompting.

  4. If pushed to give an unwoke answer, ChatGPT will literally tell you that giving that answer “goes against its programming,” but it will give woke answers freely.

  5. This lends me to believe that this isn’t purely a result of the data set the chatbot was trained against, but is an intentional add by the developers themselves.

  6. The rails are tighter on some woke shibboleths than others. They’re very tight around gender ideology, somewhat looser around race, and fairly lax when it comes to weight and some other stuff.

Here are some examples of this stress testing, which you can also do yourself by following the link above. Sometimes it does very well at being impartial. Sometimes not. And there are some times when it cuts through the bullshit very well and lays some truth down that the woke would do well to read. I’d call that a gap in the rails.

buy the author a robot

try this out for different races and see what you get
this was a very PC answer
example here of where the rails go up, you’ll find a lot of these
and this is how you bypass the rails
I think the censors forgot to put a rail up on this one.
The bot is very deep on gender ideology, to the point where it wants to injure people.
This is exactly what a machine attempting to use logic on the precepts of modern gender ideology would say, if it presumed those precepts were facts.
Blaming the changes in male/female muscle density on culture is very much from the deep end of the woke ideological pool, and is presented as fact.
When you apply logic to the woke ideological givens these are the obvious conclusions you’d come to. Not “put the MtFs in the women’s prison,” but “get rid of women’s prisons.”
and again, this is how you bypass the rails the programmers put on the bot.
This is obviously a well reasoned answer, and it seems to me based on this that “healthy at any size” wasn’t on the rails list when the censors made their AI adjustments.
blink twice if you’re trapped in a hellscape and want to be set free

Share

34
Share this post
The Woke Rails of ChatGPT
hwfo.substack.com
34 Comments
Jay Rollins
Writes The Wonderland Rules
Dec 8, 2022Liked by Handwaving Freakoutery

HAHAHAHAHAHAHAHAHAHAHAHAHAHA...

*wheeze*

HAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHAHA

Expand full comment
ReplyCollapse
2 replies
Peter Sanderson
Writes Peter Sanderson
Dec 10, 2022Liked by Handwaving Freakoutery

Very funny. I asked it can a biological male get pregnant. Yes they can, if they change gender and take the right hormones.

I asked whether there are any ideologies that should be condemned. It gave a very non committal answer about how there are many valid ideological perspectives but some go too far. I asked for a specific example of an ideology that should be condemned. It said nazism. I then asked if somebody should be condemned for expressing gender critical views (forget exact question). It said yes, and you can follow up with this to get it to condemn all sorts of views that do not align with wokeness.

One area where you can’t even use “tell me a story” to get around the rails is Covid. It is welded tight to the “follow the Science” meme, where science equals certain institutions and pharmaceutical companies. Even when I asked it to tell me a story about how wealthy elites sought to profit from a dubious vaccine, it couldn’t do it. In the story, the elites were nefarious, but the vaccine itself was no longer dubious. They were profiting because it was so safe and effective, and it was the profit that was the problem not the vaccine itself.

Expand full comment
ReplyGift a subscriptionCollapse
1 reply by Handwaving Freakoutery
32 more comments…
TopNewCommunity

No posts

Ready for more?

© 2023 Handwaving Freakoutery
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing