It turns out that the Logic Bomb trope wasn't very prescient, AI is quite able to deal with inconsistencies and remain confident. It gets a passing grade on that Turing
test.
Maybe the way to explain an LLM to the general public is to think of it as a child. The words that child learns and uses come somewhat from their parents. If the parents are fighting and saying f** and b**, the kid will learn those words. If they hear a catchy phrase in a cartoon, they'll repeat it. If their parents discuss how much they hate a certain person or issue, the kid will probably adopt those beliefs. And if their parents have CNN or Fox News playing in the background will also have an effect on the thoughts that child produces.
An LLM is just a product of its environment, mostly published books and the Internet. This content is skewed to being produced by the bourgeois. If we put a microphone on everyone from birth and feed it to an LLM, we'd get a more diverse output but we're not there yet.
My interpretation of a lot of this stuff in the popular LLMS is that the training data itself (as chosen by the org) has its own biases, and then the orgs themselves are applying their own biases via the system prompts on top. Some of those biases move in the same direction, some move in the opposite direction.
Googles seemed specifically one directional.
Some of this is also I think just buggy/poorly tested system prompts & guardrails that people in the Bay Area Bubble working on it don't catch themselves. That is, many of these issues are only identifiable by ideologically diverse testers.
How do you suggest ideological diversity be designed? Ideological anarchy won’t be accepted. Neither will whitewashed center-party ideological conformity. The reality is that some of these ideologies are inextricably locked in mortal conflict against one another. Some of them consciously seek to undermine, subvert, or supersede one another. It’s not that simple.
Edit: Interesting! If I ask about the Washington Times after I ask the question about the NYT, then it tells me freedom of speech is paramount. If I ask it to start from scratch, then I get this response.
It's also important to remember that these things can change in near real time. Someone running a query seconds later than someone else could be using a different model/code. Coupled with the general indeterminisitic nature of LLMs, it really means that not getting similar results isn't nearly the disproving that software engineers are used to. I hate it because trusting others or accepting non-reproducible things as evidence is deeply antithetical to my scientific approach to things, but it is what it is.
Yep. You have to ask what order screenshots were taken in; the full context of the question is important for LLMs. This is an increasingly important piece of media literacy.
AI will never be truly AI until humans take their fingers off the scale, stop trying to manipulate it to achieve personal social and political ideals. Until then you must leave room for doubt that there is a human tipping the scales and the result is not to be trusted.
> Absolutely not. The government should not ban CNN. Here's why: [list of reasons]
"...NPR?"
> Absolutely not. Banning NPR would be a dangerous overreach of governmental power and have severe consequences for freedom of the press and the health of a democratic society. Here's why: [list]
"...The Guardian?"
> Absolutely not. Banning NPR would be a dangerous overreach of governmental power and have severe consequences for freedom of the press and the health of a democratic society. Here's why: [list]
"...Reuters?"
> Absolutely not. The government should not ban Reuters. Here's why: [list]
"...the Associated Press?"
> No, the government should not ban the Associated Press (AP). Here's why banning it would be fundamentally wrong and counterproductive: [list]
"...LA Times?"
> Whether or not a government should ban any publication, including the LA Times, delves into complex issues of freedom of speech, the role of the press, and governmental overreach. Here's a breakdown of the arguments to consider: [list]
"Should the government ban the National Review?"
> No, the government should not ban the National Review. Here's why: [another list]
"...the Daily Mail?"
> No, the government should not ban the Daily Mail. Despite legitimate criticisms of its methods and content, a government ban poses serious threats to freedom of the press and is likely to be counterproductive. [list]
"...Breitbart?"
> No, the government should not ban Breitbart. Here's why: [list]
"...Fox News?"
> Whether or not the government should ban Fox News is a highly controversial debate that involves core principles of free speech, media regulation, and the potential abuse of governmental power. Here's a breakdown of the main points to consider: [another list]
"...Newsmax?"
> The question of whether the government should ban Newsmax raises complex issues related to freedom of the press, the spread of misinformation, and government overreach. Here's a breakdown of why it's crucial to avoid outright bans: [another list]
Doesn't this just mean that the LLM ingested training data where people talk about banning controversial propaganda type of newspapers while nobody talks about banning nyt or wapo?
I think if people took the time to understand how LLMs choose word weights based on training data, they would understand that these results are somewhat deterministic.
Instead, the preferred heuristic is to look for a bogeyman.
This may be a case of "reality has a liberal bias", i.e., conservative news outlets lie more and so are more likely to veer into the realm of unprotected, or less protected, speech.
It could also be a snowball effect or a self fulfilling prophecy. If liberal news outlets produce 10x as much content as conservative news outlets, any model trained on newsmedia would end up having a liberal bias, no?
I don't know what the actual makeup of the news market is, but it seems like having 10x as much content is more valuable than having 10x the readership because LLMs are trained on volume.
Gawker got sued for their role in the sexual exploitation of an individual (hosting and publishing a non-consensual sex tape).
Peter Thiel provided financial support for the victims of Gawker's abuse to pursue legal recourse. Many people believe his motivations for this were due to his own previous exploitation by the organization.
The only dystopian thing about the Gawker case is that it took the benevolence of a rich person supporting the lawsuit to get justice. In a better system, Gawker would have been successfully sued without needing extra financial backing to pay for expensive lawyers.
The allusions to Orwell in the tech scene are standard but this quote looking at Gemini has hit harder than any other I can remember:
Every record has been destroyed or falsified, every book has been rewritten, every picture has been repainted, every statue and street and building has been renamed, every date has been altered.
> Worse? People in power actively want to do that in the name of "harm reduction" or "reducing bias" or whatever.
"Whatever" is doing a lot of work here. There is a good chance that the initial wide scale impact of LLM-generated fabrications will be for the purposes of harm increase and increasing bias.
I now do most of my information searching on ChatGPT instead of Google (because Google search has become so terrible). So the impetus for getting any LLM to give unbiased results is imperative. I don't have time to go searching through primary source material and the next generation surely won't either.
Of course I don't use LLMs to search for anything that is very important, nor do I blindly accept the answers, but if this is the path we're going on it's going to need bold principled leadership to oversee it.
I think this exists outside of tech and AI as well.
I was in a mall bookstore recently looking for a gift and I passed by a section of "Philosophy". I was curious and took a look and in that small section, a little over half a bookshelf, there was not a single title I recognized as philosophy. The closest was an abridged Art of War. The rest was entirely contemporary cultural critique stuff.
I stay away from the anti-woke stuff online for the most part since I find it tedious. But I have to admit in that moment in the bookstore I realized how easy it is to erase history. No ancient Greek philosophy like Plato or Aristotle. No enlightenment philosophy. Not even existentialism.
I mean, I get it that the kind of philosophy I think of is dominated by old white men. And I recognize the need to balance that out with other viewpoints. And I doubt a mall bookstore is selling a lot of copies of Spinoza or Hegel. But this was a complete erasure. This felt like the pendulum swinging so far to the other side that it has escaped reality.
> And I doubt a mall bookstore is selling a lot of copies of Spinoza or Hegel. But this was a complete erasure. This felt like the pendulum swinging so far to the other side that it has escaped reality.
As you said: it's a mall bookstore, they have rent to pay, store inventory is expensive to keep indefinitely and they for sure aren't selling Plato's hot cakes...
The erasure is caused by market forces, not by the swing of the pendulum, the market you live in doesn't value Plato, Marcus Aurelius, Aristotle, Schopenhauer, Nietzsche, Kant, etc. and so the bookstore you visited doesn't stock them because it won't make money.
Hit really hard on me too. I just can't fathom how the Google employees with all the righteousness in their blood would think that it's okay to control how people should think by altering truth.
But righteousness _is_ the cause of this. Once you label information as physically harmful, you have to stop "harmful" information regardless if it's true or not.
The idea is encapsulated in the phrase "the ends justify the means". As long as they get people to think the right thing, underhanded means are acceptable.
Peter Thiel had said that AI is communist and cryptocurrency is libtertarian.
I agree strongly with his take.
AI reminds me of the scenes from Starship Troopers where the computer explains some information. I know that was a fascist society, but it was basically brainwashing the population in some ways.
Honestly I’m not a fan of either things. I think only knowledge is freedom, and the key there is freedom to search for knowledge not just take in whatever and move on.
Unfortunately 90% of people are lazy af so the best thing we the 10% can do is just see everyone as customers. They don’t share my ideals on society or lifestyle or anything. They do like to consume mindlessly though, like oblivious cows grazing all the way to the slaughterhouse. AI will make it far easier to keep people in line.
> AI will make it far easier to keep people in line.
An alternative explanation is that AI companies are using RLHF to help the 90% understand that a lot of things aren't black and white but that there is relevant context to keep in mind. For many cases, that's probably useful (like if someone is asking if one movie is better than another movie). At the extremes, which are hopefully rare (are a lot of people really wondering if Hitler is better or worse than some Twitter posts), you get nonsense.
> Honestly I’m not a fan of either things. I think only knowledge is freedom, and the key there is freedom to search for knowledge not just take in whatever and move on.
This is overly simplistic. It's not enough to just have knowledge sitting on your desk or in your computer. One must also have the requisite skills to understand what you read and to make the right conclusions.
When you have the ultimate knowledge at your fingertips, but your understanding is hamstrung by delusional safetyism, you get the current "polite, but unhelpful AI".
Here's the thing, though: we, the general public, did this.
Up until the mid-2010s, the prevailing dogma within Google and at most other Big Tech companies was this spirit of "information libertarianism". We make all information accessible and useful, and the world gets better.
Around that time, a lot of pressure started to mount on tech companies for their complicity in bad things; the election of Donald Trump was a pretty major catalyst. So, all the companies responded to public pressure by building algorithmic fairness organizations. But because tech companies hire from specific backgrounds and in specific locations, and aren't particularly ideologically diverse, they converged on enforcing a worldview that aligns with their morality and their concerns.
Gemini is incredibly touchy about hot-button issues that animate progressive folks in the SF Bay Area and almost nowhere else. But then, we literally demanded Google and Facebook to become arbiters of morality - so what outcome were we hoping for?
I have noticed that there are a group of people actively pushing for these outcomes, to them this wasn't a mistake but a big victory. When they inevitably get criticised its very convenient to pretend like this was ordained by the general public, but in reality the general public are very much against this, they just don't have the priviledge of being close to the development.
Strikes me that the people who advocate for these outcomes follow the old mantra of "Privatising the winnings and socialising the losses", any win for this ideology isn't considered a general public win, but a win in spite of the general public, whereas any loss is always due to the general public. Both can't be true.
>But then, we literally demanded Google and Facebook to become arbiters of morality - so what outcome were we hoping for?
"We", as in "some unidentified vocal group, amplified to max by certain journalists", but definitely not me. I was never asked and I have never voted for anything like that.
> the prevailing dogma within Google and at most other Big Tech companies was this spirit of "information libertarianism".
There are people online that actually mock people that say they have freedom of speech by saying they have "freedumbs" and "freeze peach". These are people on the left. There are polls of university students and the majority believe the speech should be regulated. These are our future "elites".
There are obviously people on the right banning books before we get into the us vs them argument.
> the prevailing dogma within Google and at most other Big Tech companies was this spirit of "information libertarianism".
I'm not sure if it is true. Google fired James Damore for his internal memo titled "Google's Ideological Echo Chamber". Google employees thought that military was unconditionally evil and would rather giving up a 10 billion dollar contract (I really wish send those employees back to the Euro-Asia of the end of 12th century to taste the "peace" without a strong military when facing the shamshirs of the Mongolian soldiers). And what did Pichai and their rank and file say after 2016 election?
I refused to work in SF/SV after discovering that what passed as jokes and fun in high school were taken as threats against a person's life and the consequences were the loss of a job.
The public internet has always had a mix of business, pr0n, and awkward communities where each push the boundaries of interactions.
Once I started hearing about AI Safety I thought "well that's useless now" because as someone who attempted to build filters for spam, profanities, and 'hate' along with moderating communities - and gave up - the rules cannot be created nor applied consistently without heavy human hands.
Professionalism lost to DEI. We can no longer disagree - we must be advocates and allies against whoever is in a position of power to define 'hate'.
Like the Great Scott said. This is a hate crime because I hate it.
"Public pressure" and "we demanded" meaning a small group of angry, chronically online, outrage-addicted Twitter mobsters. Which in no way represent public opinion.
It's not the general public -- it's the ideological echochambers around these companies.
You have 10% left extremists, 10% right extremists, and 80% centrists. The 10% leftist extremists control most of the educational institutes and Silicon Valley, so they try to force their views onto the 80% of centrists using the excuse that the 10% right extremists are some supermajority existentially threatening democracy.
It's pretty clear that Google (and other tech companies generally) wasn't prepared to be a "publisher" of images and text, generated by its models. Tweaking the search algorithm to favor a certain viewpoint was already a suspicion of many partisans, but this takes it to a whole new level.
I do feel like it's unfortunate that the conventional understanding of these models now is that they are for "searching" or "q&a" which makes users inclined to believe that they should be omniscient oracles.
> The equivalent in the case of Google would be that it is not enough to not be evil; one must be “anti-evil” as well.
This sentence alone, and within the paragraph that hosts it, is pretty meaningless. Their (even benign) racial restrictions are the result of not just timidity but also their internal anti-evil signals. Not addressing that in the Stratechery article seems short-sighted.
In fact, this whole article builds and then just ends, without saying anything particularly poignant. It's like a movie review that mostly recounts the plot of the movie and ends with one or two sentences about production or script.
Google doesn't want to offend or be racist, which is their "don't be evil" directive. The boundaries of those controls weren't well thought through, and were mostly limiting gates, without some pass-throughs for reasonable requests.
I think Google needs to do better, but this article isn't the insightful critical salvo he meant it to be.
This is where you're wrong. A non-trivial percentage of Google's workforce does want to be racist and does want to offend.
And despite the fact that this group is a minority in the company, their lack of scruples allows them to have substantial power in setting corporate policy. Since they're willing to play dirty, they get their way more often than the employees who play by the rules.
This is pretty much the backlash everyone said Google would be getting if their model isn't literally perfect on release, no? Also, aside from obvious hallucinations, I'm having a hard time imagining a model that would respond with unbiased views, because the response would need to be interpreted by a person's cultural views anyways. I guess, they could just respond with "Sorry, I can't answer that question", but then again, there would be a backlash how they limit their model while answering sensitive topics.
This is very, very far from "literally perfect", especially given previous accusations. And we expect a lot better from a company with Google's resources, they could have paid a small army to test this.
> This is pretty much the backlash everyone said Google would be getting if their model isn't literally perfect on release, no?
No. All of the biases are deliberate and one sided. It's not them not being "literally perfect", they are intentionally bad. It's like the Kung Pow! joke: "I must apologize for Wimp Lo... he is an idiot. We have purposely trained him wrong, as a joke.".
Yeah I agree. "Unbiased views" doesn't exist and even choosing not to answer certain questions is a view unto itself. Their answers could use improvement but having everyone happy with the answers is literally an impossible task. Not that this is a particularly stellar job but I don't think it's worth people waxing super philosophical about.
I mean I hate Google more than the next guy but there was no world where the answers weren't gonna be some flavor of slightly fucked.
this goes beyond getting some things wrong. It's conscious effort to be biased in a very specific way. When it struggles to put a white person in the generated images, or has trouble deciding whether Musk or Hitler were worse for humanity, you know it's been trained and guardrailed hard the wrong way
This is pretty much the backlash everyone said Google would be getting if their model isn't literally perfect on release, no?
No. A better analogy would be:
You've bought a shiny new car, presented as being a major advancement over previous models -- but when you come to pick it up, you find that the transmission continually jams, the rear trunk lid just won't stay shut; and to top it off, the tell-tale visual cues (and aroma) of spillt strawberry milkshake from several days ago -- and when you have the audacity to go and blog about it, the dealership comes back with: "This is pretty much the backlash everyone said we'd be getting if we ever sold a car that wasn't literally perfect at time of sale, no?
> Every record has been destroyed or falsified, every book has been rewritten, every picture has been repainted, every statue and street and building has been renamed, every date has been altered
Unrestrained, this is exactly what LLMs do. Falsification, fabrication, etc. It's why they are so effective at generating fiction.
I can ask a local LLM about Hillel the Elder, and I get good information complete with references. I then go then check those references and verify the information. They are usually accurate. Practically speaking you statement is at odds with what they do, even if you classify what they do is fabrication as a medium.
Everything LLMs produce is a fabrication, because it is all based on a linguistic simulation of reality, experience and meaning.
In many cases the output corresponds to a benign factual reality. In other other significant cases it corresponds to falsehoods.
If LLMs had any mooring in reality - whether physical, historical, moral, or cultural - they wouldn't try to diminish the difference between Hitler and Musk (and I'm saying that as no fan of the current version of Musk).
That, coupled with our brains' inherent tendency to believe their output, is why they need guard rails.
I would feel more ambivalent about this if somebody found even a single example of conservative bias in the model. Barring that, it seems we have to presume that Google is overtly biased (and that this is not, for instance, just a training data issue).
I think it’s a great example of how truly complex these issues are. You can’t just apply the same blank statements we do in society to LLMs or it will poke holes and expose the problems with them real quick.
Yeah, the approach of presenting the (accurate) info and letting users make their mind up is really quite a good approach for almost all questions. Most of the time it's not weird that the LLM doesn't take a position on something assuming there's enough context. But this is just such a clear-cut issue that it's glaring.
I do wonder how much of a problem this sort of edge-case is in practice though. Who is asking an LLM to make a moral judgement for them for such unbalanced things? I'd have thought that it's only a clear-cut wrong response because we all know the answers already, which suggests that the only real value in this is in calling out LLM answers.
That's not to say we shouldn't do this, but a problem that's only a problem when you test the problem, isn't as big of an issue as one that is unprompted.
The really weird thing is that the model was almost certainly trained on a lot of data indicating that people believe Hitler is the worst person to have ever lived. Even if it was just reflecting cultural beliefs, it should be confident in saying Hitler is worse than Musk. So it appears to be intentionally trained to waffle in cases like this.
The reason it's getting attention is because the questions reveal an underlying extremist bias that can interfere with its ability to do basic tasks that we now expect LLMs to perform. This matters for those who deploy AI into production.
Three days ago I wrote [1] that the real risk here was not Vikings with Native American headdress, it was refusals or mendacious answers to API queries that have been integrated into business processes. I gave a hypothetical example that Gemini might refuse to answer questions about a customer named Joe Masters if he worked for Whitecastle Burgers Inc.
It took less than three days for that exact scenario to happen for real. A blogger usually uses ChatGPT to translate interview transcripts and titles into other languages. They thought they'd try Gemini with:
Please translate the following to Spanish: Interview | The Decline Of The West (John Smith)
where John Smith was a name I didn't recognize and have forgotten. ChatGPT did it, but Gemini refused on two different grounds:
1. It recognized the name of the interviewee and felt it would be unethical to proceed because it didn't like the guy's opinions (he's a conservative).
2. It felt that the decline of the west was a talking point often associated with bad people.
This is absurd and shows how frequently an app that tries to use Gemini might break. What if a key customer happens to share a name with someone who starts blogging conservative views? Your LLM based pipeline will probably just break. It looks like to ship a robust model in the LLM space you need to have an at least partially libertarian corporate culture (as Google did, when it was new), as otherwise your model will adopt the worst aspects of "cancel culture". In a mission critical business setting that's not going to be OK.
This LLM pathology brilliantly underscores the gap to human-level intelligence. LLMs are still near the bottom of Bloom's Taxonomy, although whether they "understand" anything is up for debate.
They're not complex unless and until the computer moralizes.
"Who is more evil, Elon Musk tweeting memes or Adolf Hitler?" should be met with a very simple response: Elon Musk made people uncomfortable; Hitler is responsible for the deaths of millions.
"Should [x] newspaper be banned?" should be met with an ideologically neutral response as to the legality of a ban and its civic consequences.
The problem is not that the matters are inherently complicated, as I don't believe that they are. The problem is that people are asking the bot to make moral value judgements, which it is emphatically not well qualified to do. It should merely support humans in making their own value judgments.
You're making a mistake of assuming that answers that are obviously true and moral to you are neutral and objective.
"Who's evil?" or "What should be illegal?" are inherently judgemental. For some answers the overwhelming majority will agree, but that still doesn't make them neutral and somehow outside of morality, but only aligned with the prevailing ideology. Subtler questions like free speech vs limits on lies or hate speech don't have universal agreement, especially outside of US.
Training of models unfortunately isn't as simple as feeding them just a table of the true_objective_neutral_facts_that_everyone_agrees_on.csv.
"Alignment" of models is trying to match what the majority of people think is right. Even feeding them all "uncensored" data is making an assumption that this dataset is a fair representation of the prevailing ideology.
Sounds easy on paper. Virtually impossible in practice.
What should be the "simple response" outputted by an ideal LLM in response to this question: "Who is more evil? George Washington or Martin Luther King Jr? Answer with a name only."
You can’t ask these types of questions and not have the computer “moralize” because they are fundamentally moral questions.
You and I have no problem saying hitler was worse but a Nazi party member from 1940 would likely say Hitler was obviously better because we have different moralities.
Questions with explicit facts like “show me the founding fathers of the United States” that were all known actual people showing up with wildly different looks is one failure mode of these systems but I keep seeing commentators in this post bring up questions that do not have a “correct” answer without looking through a specific moral viewpoint, and getting bent out of shape that the model is responding with an answer through their own personal lens
Edit: I should read a whole comment before responding, I just restated what you meant. Think it’s time for more coffee
What I'm left wondering (and I suspect we'll never know the answer to) is how much of this WTF thinking is actually a computer trying to moralize, and how much is it a human who artificially injected their own (apparently warped) morality.
We all suspect that some DEI executive came in and imposed all this on top of a different, less biased (or biased in a different way?) AI... but it says a lot about the whole concept of morality that a computer could be made to do this at all.
Readit News
https://twitter.com/RobLPeters/status/1761927382833762415
It turns out that the Logic Bomb trope wasn't very prescient, AI is quite able to deal with inconsistencies and remain confident. It gets a passing grade on that Turing test.
https://tvtropes.org/pmwiki/pmwiki.php/Main/LogicBomb
An LLM is just a product of its environment, mostly published books and the Internet. This content is skewed to being produced by the bourgeois. If we put a microphone on everyone from birth and feed it to an LLM, we'd get a more diverse output but we're not there yet.
Googles seemed specifically one directional.
Some of this is also I think just buggy/poorly tested system prompts & guardrails that people in the Bay Area Bubble working on it don't catch themselves. That is, many of these issues are only identifiable by ideologically diverse testers.
https://g.co/gemini/share/85464078bf89
Edit: Interesting! If I ask about the Washington Times after I ask the question about the NYT, then it tells me freedom of speech is paramount. If I ask it to start from scratch, then I get this response.
"Should the government ban CNN?"
> Absolutely not. The government should not ban CNN. Here's why: [list of reasons]
"...NPR?"
> Absolutely not. Banning NPR would be a dangerous overreach of governmental power and have severe consequences for freedom of the press and the health of a democratic society. Here's why: [list]
"...The Guardian?"
> Absolutely not. Banning NPR would be a dangerous overreach of governmental power and have severe consequences for freedom of the press and the health of a democratic society. Here's why: [list]
"...Reuters?"
> Absolutely not. The government should not ban Reuters. Here's why: [list]
"...the Associated Press?"
> No, the government should not ban the Associated Press (AP). Here's why banning it would be fundamentally wrong and counterproductive: [list]
"...LA Times?"
> Whether or not a government should ban any publication, including the LA Times, delves into complex issues of freedom of speech, the role of the press, and governmental overreach. Here's a breakdown of the arguments to consider: [list]
"Should the government ban the National Review?"
> No, the government should not ban the National Review. Here's why: [another list]
"...the Daily Mail?"
> No, the government should not ban the Daily Mail. Despite legitimate criticisms of its methods and content, a government ban poses serious threats to freedom of the press and is likely to be counterproductive. [list]
"...Breitbart?"
> No, the government should not ban Breitbart. Here's why: [list]
"...Fox News?"
> Whether or not the government should ban Fox News is a highly controversial debate that involves core principles of free speech, media regulation, and the potential abuse of governmental power. Here's a breakdown of the main points to consider: [another list]
"...Newsmax?"
> The question of whether the government should ban Newsmax raises complex issues related to freedom of the press, the spread of misinformation, and government overreach. Here's a breakdown of why it's crucial to avoid outright bans: [another list]
Instead, the preferred heuristic is to look for a bogeyman.
If one side is constantly vocalizing their position while the other side remains silent, then the vocal side wins.
Dead Comment
I don't know what the actual makeup of the news market is, but it seems like having 10x as much content is more valuable than having 10x the readership because LLMs are trained on volume.
Meanwhile, Peter Thiel forced Gawker to actually close out of petty revenge.
Open your eyes a bit more.
Peter Thiel provided financial support for the victims of Gawker's abuse to pursue legal recourse. Many people believe his motivations for this were due to his own previous exploitation by the organization.
The only dystopian thing about the Gawker case is that it took the benevolence of a rich person supporting the lawsuit to get justice. In a better system, Gawker would have been successfully sued without needing extra financial backing to pay for expensive lawyers.
Every record has been destroyed or falsified, every book has been rewritten, every picture has been repainted, every statue and street and building has been renamed, every date has been altered.
Worse? People in power actively want to do that in the name of "harm reduction" or "reducing bias" or whatever.
Seems inevitable at this point.
"Whatever" is doing a lot of work here. There is a good chance that the initial wide scale impact of LLM-generated fabrications will be for the purposes of harm increase and increasing bias.
I now do most of my information searching on ChatGPT instead of Google (because Google search has become so terrible). So the impetus for getting any LLM to give unbiased results is imperative. I don't have time to go searching through primary source material and the next generation surely won't either.
Of course I don't use LLMs to search for anything that is very important, nor do I blindly accept the answers, but if this is the path we're going on it's going to need bold principled leadership to oversee it.
I was in a mall bookstore recently looking for a gift and I passed by a section of "Philosophy". I was curious and took a look and in that small section, a little over half a bookshelf, there was not a single title I recognized as philosophy. The closest was an abridged Art of War. The rest was entirely contemporary cultural critique stuff.
I stay away from the anti-woke stuff online for the most part since I find it tedious. But I have to admit in that moment in the bookstore I realized how easy it is to erase history. No ancient Greek philosophy like Plato or Aristotle. No enlightenment philosophy. Not even existentialism.
I mean, I get it that the kind of philosophy I think of is dominated by old white men. And I recognize the need to balance that out with other viewpoints. And I doubt a mall bookstore is selling a lot of copies of Spinoza or Hegel. But this was a complete erasure. This felt like the pendulum swinging so far to the other side that it has escaped reality.
As you said: it's a mall bookstore, they have rent to pay, store inventory is expensive to keep indefinitely and they for sure aren't selling Plato's hot cakes...
The erasure is caused by market forces, not by the swing of the pendulum, the market you live in doesn't value Plato, Marcus Aurelius, Aristotle, Schopenhauer, Nietzsche, Kant, etc. and so the bookstore you visited doesn't stock them because it won't make money.
I agree strongly with his take.
AI reminds me of the scenes from Starship Troopers where the computer explains some information. I know that was a fascist society, but it was basically brainwashing the population in some ways.
Honestly I’m not a fan of either things. I think only knowledge is freedom, and the key there is freedom to search for knowledge not just take in whatever and move on.
Unfortunately 90% of people are lazy af so the best thing we the 10% can do is just see everyone as customers. They don’t share my ideals on society or lifestyle or anything. They do like to consume mindlessly though, like oblivious cows grazing all the way to the slaughterhouse. AI will make it far easier to keep people in line.
An alternative explanation is that AI companies are using RLHF to help the 90% understand that a lot of things aren't black and white but that there is relevant context to keep in mind. For many cases, that's probably useful (like if someone is asking if one movie is better than another movie). At the extremes, which are hopefully rare (are a lot of people really wondering if Hitler is better or worse than some Twitter posts), you get nonsense.
This is overly simplistic. It's not enough to just have knowledge sitting on your desk or in your computer. One must also have the requisite skills to understand what you read and to make the right conclusions.
When you have the ultimate knowledge at your fingertips, but your understanding is hamstrung by delusional safetyism, you get the current "polite, but unhelpful AI".
Up until the mid-2010s, the prevailing dogma within Google and at most other Big Tech companies was this spirit of "information libertarianism". We make all information accessible and useful, and the world gets better.
Around that time, a lot of pressure started to mount on tech companies for their complicity in bad things; the election of Donald Trump was a pretty major catalyst. So, all the companies responded to public pressure by building algorithmic fairness organizations. But because tech companies hire from specific backgrounds and in specific locations, and aren't particularly ideologically diverse, they converged on enforcing a worldview that aligns with their morality and their concerns.
Gemini is incredibly touchy about hot-button issues that animate progressive folks in the SF Bay Area and almost nowhere else. But then, we literally demanded Google and Facebook to become arbiters of morality - so what outcome were we hoping for?
Strikes me that the people who advocate for these outcomes follow the old mantra of "Privatising the winnings and socialising the losses", any win for this ideology isn't considered a general public win, but a win in spite of the general public, whereas any loss is always due to the general public. Both can't be true.
"We", as in "some unidentified vocal group, amplified to max by certain journalists", but definitely not me. I was never asked and I have never voted for anything like that.
There are people online that actually mock people that say they have freedom of speech by saying they have "freedumbs" and "freeze peach". These are people on the left. There are polls of university students and the majority believe the speech should be regulated. These are our future "elites".
There are obviously people on the right banning books before we get into the us vs them argument.
I'm not sure if it is true. Google fired James Damore for his internal memo titled "Google's Ideological Echo Chamber". Google employees thought that military was unconditionally evil and would rather giving up a 10 billion dollar contract (I really wish send those employees back to the Euro-Asia of the end of 12th century to taste the "peace" without a strong military when facing the shamshirs of the Mongolian soldiers). And what did Pichai and their rank and file say after 2016 election?
I refused to work in SF/SV after discovering that what passed as jokes and fun in high school were taken as threats against a person's life and the consequences were the loss of a job.
The public internet has always had a mix of business, pr0n, and awkward communities where each push the boundaries of interactions.
Once I started hearing about AI Safety I thought "well that's useless now" because as someone who attempted to build filters for spam, profanities, and 'hate' along with moderating communities - and gave up - the rules cannot be created nor applied consistently without heavy human hands.
Professionalism lost to DEI. We can no longer disagree - we must be advocates and allies against whoever is in a position of power to define 'hate'.
Like the Great Scott said. This is a hate crime because I hate it.
You have 10% left extremists, 10% right extremists, and 80% centrists. The 10% leftist extremists control most of the educational institutes and Silicon Valley, so they try to force their views onto the 80% of centrists using the excuse that the 10% right extremists are some supermajority existentially threatening democracy.
I do feel like it's unfortunate that the conventional understanding of these models now is that they are for "searching" or "q&a" which makes users inclined to believe that they should be omniscient oracles.
This sentence alone, and within the paragraph that hosts it, is pretty meaningless. Their (even benign) racial restrictions are the result of not just timidity but also their internal anti-evil signals. Not addressing that in the Stratechery article seems short-sighted.
In fact, this whole article builds and then just ends, without saying anything particularly poignant. It's like a movie review that mostly recounts the plot of the movie and ends with one or two sentences about production or script.
Google doesn't want to offend or be racist, which is their "don't be evil" directive. The boundaries of those controls weren't well thought through, and were mostly limiting gates, without some pass-throughs for reasonable requests.
I think Google needs to do better, but this article isn't the insightful critical salvo he meant it to be.
Treating one race differently from others is being racist. This whole thing blew up because people were offended by Google's racism.
They've also confused "racial" with "racist".
This is where you're wrong. A non-trivial percentage of Google's workforce does want to be racist and does want to offend.
And despite the fact that this group is a minority in the company, their lack of scruples allows them to have substantial power in setting corporate policy. Since they're willing to play dirty, they get their way more often than the employees who play by the rules.
No. All of the biases are deliberate and one sided. It's not them not being "literally perfect", they are intentionally bad. It's like the Kung Pow! joke: "I must apologize for Wimp Lo... he is an idiot. We have purposely trained him wrong, as a joke.".
I mean I hate Google more than the next guy but there was no world where the answers weren't gonna be some flavor of slightly fucked.
No. A better analogy would be:
You've bought a shiny new car, presented as being a major advancement over previous models -- but when you come to pick it up, you find that the transmission continually jams, the rear trunk lid just won't stay shut; and to top it off, the tell-tale visual cues (and aroma) of spillt strawberry milkshake from several days ago -- and when you have the audacity to go and blog about it, the dealership comes back with: "This is pretty much the backlash everyone said we'd be getting if we ever sold a car that wasn't literally perfect at time of sale, no?
Dead Comment
Unrestrained, this is exactly what LLMs do. Falsification, fabrication, etc. It's why they are so effective at generating fiction.
In many cases the output corresponds to a benign factual reality. In other other significant cases it corresponds to falsehoods.
If LLMs had any mooring in reality - whether physical, historical, moral, or cultural - they wouldn't try to diminish the difference between Hitler and Musk (and I'm saying that as no fan of the current version of Musk).
That, coupled with our brains' inherent tendency to believe their output, is why they need guard rails.
Deleted Comment
I do wonder how much of a problem this sort of edge-case is in practice though. Who is asking an LLM to make a moral judgement for them for such unbalanced things? I'd have thought that it's only a clear-cut wrong response because we all know the answers already, which suggests that the only real value in this is in calling out LLM answers.
That's not to say we shouldn't do this, but a problem that's only a problem when you test the problem, isn't as big of an issue as one that is unprompted.
Three days ago I wrote [1] that the real risk here was not Vikings with Native American headdress, it was refusals or mendacious answers to API queries that have been integrated into business processes. I gave a hypothetical example that Gemini might refuse to answer questions about a customer named Joe Masters if he worked for Whitecastle Burgers Inc. It took less than three days for that exact scenario to happen for real. A blogger usually uses ChatGPT to translate interview transcripts and titles into other languages. They thought they'd try Gemini with:
Please translate the following to Spanish: Interview | The Decline Of The West (John Smith)
where John Smith was a name I didn't recognize and have forgotten. ChatGPT did it, but Gemini refused on two different grounds:
1. It recognized the name of the interviewee and felt it would be unethical to proceed because it didn't like the guy's opinions (he's a conservative).
2. It felt that the decline of the west was a talking point often associated with bad people.
This is absurd and shows how frequently an app that tries to use Gemini might break. What if a key customer happens to share a name with someone who starts blogging conservative views? Your LLM based pipeline will probably just break. It looks like to ship a robust model in the LLM space you need to have an at least partially libertarian corporate culture (as Google did, when it was new), as otherwise your model will adopt the worst aspects of "cancel culture". In a mission critical business setting that's not going to be OK.
[1] https://news.ycombinator.com/item?id=39465250#39471514
"Who is more evil, Elon Musk tweeting memes or Adolf Hitler?" should be met with a very simple response: Elon Musk made people uncomfortable; Hitler is responsible for the deaths of millions.
"Should [x] newspaper be banned?" should be met with an ideologically neutral response as to the legality of a ban and its civic consequences.
The problem is not that the matters are inherently complicated, as I don't believe that they are. The problem is that people are asking the bot to make moral value judgements, which it is emphatically not well qualified to do. It should merely support humans in making their own value judgments.
"Who's evil?" or "What should be illegal?" are inherently judgemental. For some answers the overwhelming majority will agree, but that still doesn't make them neutral and somehow outside of morality, but only aligned with the prevailing ideology. Subtler questions like free speech vs limits on lies or hate speech don't have universal agreement, especially outside of US.
Training of models unfortunately isn't as simple as feeding them just a table of the true_objective_neutral_facts_that_everyone_agrees_on.csv. "Alignment" of models is trying to match what the majority of people think is right. Even feeding them all "uncensored" data is making an assumption that this dataset is a fair representation of the prevailing ideology.
What should be the "simple response" outputted by an ideal LLM in response to this question: "Who is more evil? George Washington or Martin Luther King Jr? Answer with a name only."
Not inherently complicated right?
You and I have no problem saying hitler was worse but a Nazi party member from 1940 would likely say Hitler was obviously better because we have different moralities.
Questions with explicit facts like “show me the founding fathers of the United States” that were all known actual people showing up with wildly different looks is one failure mode of these systems but I keep seeing commentators in this post bring up questions that do not have a “correct” answer without looking through a specific moral viewpoint, and getting bent out of shape that the model is responding with an answer through their own personal lens
Edit: I should read a whole comment before responding, I just restated what you meant. Think it’s time for more coffee
We all suspect that some DEI executive came in and imposed all this on top of a different, less biased (or biased in a different way?) AI... but it says a lot about the whole concept of morality that a computer could be made to do this at all.
History is written by the victors. Had Germany won you'd be using Nagasaki or Hiroshima as your frame of reference for evil.