Oh, this may harm you. This is to prevent you from being harmed. No, you can’t know how it can harm you, or how exactly this protects you.
AI behavior guardrails should be public
301–310 of 350 posts
Re: AI behavior guardrails should be public
#302Earlier quoted context omitted.
You want large tech companies "creating reality" on behalf of everyone else? They're not even democratic institutions that we vote on. You trust they will get it right? Our benevolent super rich overlords.
Its not really a question about want, its a question about facts. Their actions will make a significant mark on the future. So far it seems like they are trying to promote positive changes such as inclusion and equality. Which is far far far fucking really infinitely far better than trying to promote exclusion and inequality
There’s a huge difference between filling in gaps with diversity and refusing to make innocuous pictures a user explicitly asked for—except only when “white” is involved while making any picture with black people in it even when ahistorical.
Re: AI behavior guardrails should be public
#303Harris and who I think was either Hughes or Stewart a podcast where they talked about how cringey and out of touch the elite are on the topic of race or wokeness in general. This faux pas on google's part couldn't be a better illustration of this. A bunch of wealthy rich tech geeks programming an AI to show racial diversity in what were/are unambiguously not diverse settings. They're just so painfully divorced from r…
Watch your opinion on this get silenced in subtle ways. From gaslighting to thread nerfing to vote locking.... Ask why anyone would engage in those behaviours vs the merit of the arguments and the voice of the people. The strings are revealing themselves so incredibly fast. edit: my first flagged! silence is deafening ^_^. This is achieved by nerfing the thread from public view, then allow the truly caustic to alter…
Could you please stop posting unsubstantive comments and flamebait and otherwise breaking the site guidelines? You've unfortunately been doing it repeatedly.
If you wouldn't mind reviewing https://news.ycombinator.com/newsguidelines.html and taking the intended spirit of the site more to heart, we'd be grateful.
Re: AI behavior guardrails should be public
#304Earlier quoted context omitted.
Humans do look like gorillas. We're related. It's natural that an imperfect program that deals with images will will mistake the two. Humans, unfortunately, are offended if you imply they look like gorillas. What's a good fix? Human sensitivity is arbitrary, so the fix is going to tend to be arbitrary too.
A good fix would, in my opinion, understanding how the algorithm is actually categorizing and why it miss-recognized gorillas and humans. If the algorithm doesn't work well they have problems to solve.
But this is not an algorithm. It's a trained neural network which is practically a black box. The best they can do is train it on different data sets, but that's impractical.
Re: AI behavior guardrails should be public
#305I strongly suspect Google tried really, really hard here to overcome the criticism is got with previous image recognition models saying that black people looked like gorillas. I am not really sure what I would want out of an image generation system, but I think Google's system probably went too far in trying to incorporate diversity in image generation.
They have now added a strong bias for generating black people now. Some have prompted to generate a picture of a German WW2 soldier, and now there are many pictures of black people floating around in NAZI uniforms.
I think their strategy to "enhance" outcomes is very misdirected.
The most widely used base models to really fine tune models are those that are not censored and I think you have to construct a problem to find one here. Of course AI won't generate a perfect world, but this is something that will probably only get better with time when users are able to adapt models to their liking.
Re: AI behavior guardrails should be public
#306Earlier quoted context omitted.
> Where do we go from here? opensource models and training sets. So basically the "secret sauce" minus the hardware. I don't see it happening voluntarily.
I see it as not unlikely that there'll be a campaign to sigmatize, if not outright ban, open source models on the grounds of "safety". I'm quite surprised at how relatively unimpeded the distribution of image generation models has been, so far
What you're predicting has already started. Two weeks ago Geoffrey Hinton gave a speech advocating banning open source AI models (see e.g.: https://thelogic.co/news/ai-cant-be-slowed-down-hinton-says-... ).
I'm surprised there wasn't an HN thread about it at the time.
Re: AI behavior guardrails should be public
#307This is a tough problem. On one hand, if you're a large organization, you need to limit your liability. No one wants the PR nightmare. Unfortunately, there will be an inverse correlation between usefulness and number of users the model supports.
This is one reason why for internal use/private/corporate models, which is the vast majority of use cases, it makes sense to fine-tune your own.
Re: AI behavior guardrails should be public
#308Earlier quoted context omitted.
Its not really a question about want, its a question about facts. Their actions will make a significant mark on the future. So far it seems like they are trying to promote positive changes such as inclusion and equality. Which is far far far fucking really infinitely far better than trying to promote exclusion and inequality
Can you please explain how outright refusing to draw an image with from the prompt "white male scientist", and instead giving a lecture on how their race is irrelevant to their occupation, but then happily drawing the requested image when prompted for "black female scientist", is promoting inclusion and equality?
It is pretty clear to me.
Reality has a bias, most scientist in the world are white males.
This IA is overtuned in the opossite direction to inspire kids who have not ever seen a person like them, not white, in those kind of jobs.
Re: AI behavior guardrails should be public
#309Earlier quoted context omitted.
> "Generate a scene of 17th century kings of Scotland playing golf." -> The result should not be a bunch of black men and Asian women dressed up as Scottish kings, it should be a bunch of white guys. It works in bing, at least: https://www.bing.com/images/create/a-picture-of-some-17th-ce...
I don't know that this sheds light on anything but I was curious... a picture of some 21st century scottish kings playing golf (all white) https://www.bing.com/images/create/a-picture-of-some-21st-ce... a picture of some 22nd century scottish kings playing golf (all white) https://www.bing.com/images/create/a-picture-of-some-22nd-ce... a picture of some 23rd century scottish kings playing golf (all white) https://www…
Two weeks ago I tried the following prompts, and I was very surprised by the "diversity" of my dark age soldiers:
https://www.bing.com/images/create/selfy-of-a-group-of-dark-...
https://www.bing.com/images/create/selfy-of-a-group-of-dark-...
Re: AI behavior guardrails should be public
#310Earlier quoted context omitted.
A good fix would, in my opinion, understanding how the algorithm is actually categorizing and why it miss-recognized gorillas and humans. If the algorithm doesn't work well they have problems to solve.
But this is not an algorithm. It's a trained neural network which is practically a black box. The best they can do is train it on different data sets, but that's impractical.
That's exactly the problem I was trying to reference. The algorithms and data models are black boxes - we don't know wat they learned or why they learned it. That setup can't be intentionally fixed, and more importantly we wouldn't know if it was fixed because we can only validate input/output pairs.