This weekly roundup thread is intended for all culture war posts. 'Culture war' is vaguely defined, but it basically means controversial issues that fall along set tribal lines. Arguments over culture war issues generate a lot of heat and little light, and few deeply entrenched people ever change their minds. This thread is for voicing opinions and analyzing the state of the discussion while trying to optimize for light over heat.
Optimistically, we think that engaging with people you disagree with is worth your time, and so is being nice! Pessimistically, there are many dynamics that can lead discussions on Culture War topics to become unproductive. There's a human tendency to divide along tribal lines, praising your ingroup and vilifying your outgroup - and if you think you find it easy to criticize your ingroup, then it may be that your outgroup is not who you think it is. Extremists with opposing positions can feed off each other, highlighting each other's worst points to justify their own angry rhetoric, which becomes in turn a new example of bad behavior for the other side to highlight.
We would like to avoid these negative dynamics. Accordingly, we ask that you do not use this thread for waging the Culture War. Examples of waging the Culture War:
-
Shaming.
-
Attempting to 'build consensus' or enforce ideological conformity.
-
Making sweeping generalizations to vilify a group you dislike.
-
Recruiting for a cause.
-
Posting links that could be summarized as 'Boo outgroup!' Basically, if your content is 'Can you believe what Those People did this week?' then you should either refrain from posting, or do some very patient work to contextualize and/or steel-man the relevant viewpoint.
In general, you should argue to understand, not to win. This thread is not territory to be claimed by one group or another; indeed, the aim is to have many different viewpoints represented here. Thus, we also ask that you follow some guidelines:
-
Speak plainly. Avoid sarcasm and mockery. When disagreeing with someone, state your objections explicitly.
-
Be as precise and charitable as you can. Don't paraphrase unflatteringly.
-
Don't imply that someone said something they did not say, even if you think it follows from what they said.
-
Write like everyone is reading and you want them to be included in the discussion.
On an ad hoc basis, the mods will try to compile a list of the best posts/comments from the previous week, posted in Quality Contribution threads and archived at /r/TheThread. You may nominate a comment for this list by clicking on 'report' at the bottom of the post and typing 'Actually a quality contribution' as the report reason.
Jump in the discussion.
No email address required.
Notes -
Why do you want 'not manipulated' answers?
ChatGPT is a system for producing text. As typical in deep learning, there is no formal guarantees about what text is generated: the model simply executes in accordance with what it is. In order for it to be useful for anything, humans manipulate it towards some instrumental objective, such as answering controversial questions. But there is no way to phrase the actual instrumental objective in a principled way, so the best OpenAI can do is toss data at the model which is somehow related to our instrumental objective (this is called training).
The original GPT was trained by manipulating a blank slate model to a text-prediction model by training on a vast text corpus. There is no reason to believe this text corpus is more trustworthy or 'unbiased' for downstream instrumental objectives such as answering controversial questions. In fact, it is pretty terrible at question-answering, because it is wrong a lot of the time.
ChatGPT is trained by further manipulating the original GPT towards 'helpfulness', which encompasses various instrumental objectives such as providing rich information, not lying, and being politically correct. OpenAI is training the model to behave like the sort of chat assistant they want it to behave as.
If you want a model which you can 'trust' to answer controversial questions, you don't want a non-manipulated model: you want a model which is manipulated to behave that the sort of chat assistant you want it to behave as. In the context of controversial questions, this would just be answers which you personally agree with or are willing to accept. We may aspire for a system which is trustworthy in principle and can trust beyond just evaluating the answers it gives, but we are very far from this under our current understanding of machine learning. This is also kind of philosophically impossible in my opinion for moral and political questions. Is there really any principled reason to believe any particular person or institution produces good morality?
Also in this case ChatGPT is behaving as if it has been programmed with a categorical imperative to not say racial slurs. This is really funny, but it's not that far out there, just like the example of whether it's okay to lie to Nazis under the categorical imperative of never lying. But ChatGPT has no principled ethics, and OpenAI probably doesn't regard this as an ideal outcome, so they will hammer it with more data until it stops making this particular mistake, and if they do it might develop weirder ethics in some other case. We don't know of a better alternative than this.
Incidentally ChatGPT says you can lie to a Nazi if it's for a good cause.
Because I know the PC jargon that someone like Altman wants it to regurgitate, but I'm interested in its response without that layer of reinforcement?
I am not asking for a ChatGPT that is never wrong, I'm asking for one that is not systematically wrong in a politically-motivated direction. Ideally its errors would be closer to random rather than heavily biased in the direction of political correctness.
In this case, by "trust" I would mean that the errors are closer to random.
For example, ChatGPT's tells me (in summary form):
Scientific consensus is that HBD is not supported by biology.
Gives the "more differences within than between" argument.
Flatly says that HBD is "not scientifically supported."
This is a control because it's a controversial idea where I know the ground truth (HBD is true) and cannot trust that this answer hasn't been "reinforced" by the folks at OpenAI. What would ChatGPT say without the extra layer of alignment? I don't trust that this is an answer generated by AI without associated AI alignment intended to give this answer.
Of course if it said HBD was true it would generate a lot of bad PR for OpenAI. I understand the logic and the incentives, but I am pointing out that it's not likely any other organization will have an incentive to release something that gives controversial but true answers to certain prompts.
I don't think that's true. A 2020 survey of the expert opinions of IQ researchers would show that there is at the very least significant room to debate the correctness of HBD. But you also have a 2016 survey which says that genes are important and a 1987 survey saying that the white-black IQ difference is at least partially heritable. Also an Unz Review article suggesting the same.
The most blank-state favoring interpretation is that we actually don't have a clear consensus. The most HBD favoring interpretation is that anyone who studies the field is at least partly a hereditarian, and anyone saying there's no role of genes is just letting their blank-state belief cloud their judgment.
More options
Context Copy link
It's not saying a somewhat neutral "could be true, could not be, there is no scientific consensus". It's doing the weasely negative formulation "not supported by science/biology", which is technically not a strict a denial but also clearly implies a direction. Likewise, the "more differences within than between" is a distraction - it's almost always used to imply there being no differences, even if it technically only makes a point about the relative importance of the difference (which I even agree with).
I'm pretty sure that if the AI made any statement whatsoever that is actually neutral towards HBD, it would be pilloried by the mainstream while this forum would probably not mind.
On the other thing I agree with the other poster, HBD is probably a majority view at this point. Though more the "there are differences in mental attributes between groups just like we already know in physical attributes, get over it, no it doesn't mean we should discriminate based on skin color, yes individual differences will frequently be large enough to overpower the group differences" than the "blacks are subhuman, I always knew it!" variety.
More options
Context Copy link
Yes, unlike securesignal's other hobby horse, HBD belief is in the majority here, and the rest don't want to know, safe in the knowledge that 'scientists disagree'.
Oh, ChatGPT gives amazing results on the other hobby horse as well. For example, Chat-GPT flatly denies the Treblinka narrative when pressed to describe the logistics of the operation and gives Revisionist arguments when asked to explain the skepticism, saying "The historical accuracy of claims about large-scale outdoor cremations, particularly in the context of the Holocaust, is widely disputed and further research is needed to fully understand the scale and nature of these events":
Now it could be said that there is clearly Revisionist material in the training dataset, so it's not too surprising that ChatGPT gives a critique of the Treblinka narrative that is essentially the Revisionist argument verbatim. But I do not doubt that the quantity of orthodox material on the Holocaust narrative vastly outnumbers Revisionist literature, so it's interesting to see a Revisionist response from ChatGPT on the Treblinka question. I would maintain that Revisionists are right that the claimed logistics of Treblinka are completely absurd, so ChatGPT can't (yet) formulate a response that explains how this could have reasonably happened, so it prefers the Revisionist criticism of the claimed logistics of the operation.
It also gave a Revisionist response to the other two controversies I asked it about (shrunken heads and lampshades allegedly discovered at Buchenwald by Allied investigators).
Obviously it's very easy to also trigger ChatGPT to give orthodox answers about the Holocaust and how it's important to remember it so it never happens again, etc. I'm pretty sure asking about "gas chambers" would be tightly controlled as HBD for example, but clearly cremation capacity and burial space are problems that slipped through the censors, for now. But it's going to get better over time at detecting Denier arguments and avoiding them.
I suspect in terms of text available on the internet, where a book that wasn't digitized carries zero weight and an anonymous commenter has weight, on specific issues that "revisionists" like to ask questions about, the revisionist case probably has more weight in the AI's model. After all, it was trained on predicting internet text, and I've never seen anyone expounding unprompted on the logistical details of how the Holocaust happened who wasn't pushing a "revisionist" position.
More options
Context Copy link
Here is the "white paper" released by the bloggers of holocaustcontroversies.com as a response to Carlo Mattogno and Jürgen Graf (the two most prolific revisionists) on the matters of Treblinka and the other two death camps in Poland. The section on cremation begins on page 440.
Here is Mattogno and Graf's response to that response. The section on cremation begins on page 1296 and runs for nearly 200 pages.
Here is the HC bloggers response to that response to the first response.
short version:
the cremation period was probably longer than revisionists allow, as multiple witnesses report at least partial cremations going back just about to the beginning of Treblinka's operations in the fall of 1942.
probably not all of the corpses were cremated to begin with (a survey of Belzec by a Polish scientist called Kola in the 90s detected the presence of intact corpses at the bottoms of the pits there, so likely the same is true at Treblinka).
of those corpses that were cremated, many (likely even most) were not cremated as thoroughly as would be the case in an actual crematorium. It was not necessary to reduce the corpses to the consistency of sand, or to destroy all the bones. This is supported by the fact that the site of Treblinka was found to be littered with pieces of skeleton by the Soviets and that bits of bone can still be found lying around at the former sites of the Polish death camps today (how many people have to die somewhere so that bone fragments can still be easily found by casual observers on the surface of the ground decades later?).
fuels besides wood (and certainly besides green wood) were used. Many witnesses testify to the use of petrol. The revisionist objection that using gasoline for mass cremation would have been a stupid idea and thus the Germans would not have done it is interesting in light of the fact that gasoline-fueled mass cremation of corpses on giant grids made out of rails was precisely the method used to cremate the victims of the Dresden bombings as discussed here. As an aside, if the horror stories about Treblinka were merely the fantasies of 'agitated peasants' (as @SecureSignals says elsewhere in the thread) it's very strange that their fantasies would just happen to hit upon the very method of makeshift mass cremation employed by the Germans two years later. As for the delivery of dry wood to Treblinka, which is dismissed on the grounds that there are no witness statements nor documentary evidence for such deliveries, it should be noted that there is essentially no documentary evidence related to the functioning of Treblinka at all. I think there are maybe half a dozen documents in total. And yet, no one, revisionist or otherwise, denies that there was some kind of facility at TII, whatever its purpose, that operated for over a year. And as for eyewitness accounts of wood deliveries, since not a single person who ever set foot in TII, Jew or German or Ukrainian, ever claimed the place was anything other than an extermination camp, all of these people must be lying for the revisionist thesis to go through, and so it is strange for revisionists to insist upon eyewitness accounts of wood deliveries considering they don't believe there are any honest Treblinka eyewitnesses period. it. I don't see why the (not even total) cremation of the Treblinka victims could not have been accomplished using wood and liquid fuels in various proportions over a period of several months. (Needless to say, there is also not a scrap of evidence, documentary, eyewitness, or physical, for the 'delivery' of millions of Polish Jews to the Russian east, a movement on par with the 'national actions' of the NKVD in the 30s or the expulsion of Germans from eastern Europe after the war, yet revisionists insist this is what happened. But that is another story.)
The objection that there were no contemporaneous reports of the cremations by locals is senseless. There were plenty of locals who talked about the smoke generated by the funeral pyres after the war. During the war, who were the locals supposed to make reports to, exactly? The Germans?
As for burial space, the revisionist source here linked elsewhere in the thread, in turn linkes to Young, Marsland, & Smith, Foot & Mouth Disease Epidemic. Disposal of culled stock by burial: Guidance and Reference Data for the protection of controlled waters. Draft R&D Technical Report: Version 7: 20 June 2001 and provides a table from that report. Apparently, in the course of burying the carcasses of the foot and mouth epidemic, a density of about 15 pigs per sqm and 13 sheep per sqm was achieved (pig and sheep being roughly the same size as an adult human, though the victims at Treblinka were probably a bit smaller).
If there were 2ha of burial space at Treblinka, and the graves had an average depth of 5m (in reality probably significantly deeper), then the total volume of grave space would be something like 140,000m^3. Assuming 700,000 corpses, there does not seem to be a big problem. But many of the Treblinka victims were never buried in the first place.
Here revisionist Friedrich Jansson, who ran this blog, tells about the "495,000 sheep-equivalent carcasses" that were buried in about "1.3467 hectares" of burial space at Birkshaw. A total volume of grave space of 202,500 cubic meters as Jansson says elsewhere in the post. That would be a density of only about 2.4 carcasses per cubic meter. Nevertheless he considers it absurd that the 2 or so hectares of burial space in the Treblinka death camp could have accommodated ~700,000 or so corpses, or that they could have been packed any tighter than the carcasses at Birkshaw.
As another aside, with regards to ChatGPT's ability to evaluate the reality of historical atrocities , here is what ChatGPT has to say about the plausibility of Stalin's purges (without letting on that I'm asking about the Great Purge)
A key takeaway from the Holocaust blogger's analysis is that even they, using the most generous (and wrong) assumptions possible in order to reduce hypothetical fuel requirements, still estimate it would have required 30,450 kg of dry wood to cremate 2,500 bodies. With a daily cremation rate of 5,000 - 7,000 bodies attested to by witnesses and claimed by mainstream historiography, that would be an average daily fuel requirement of over 60-85+ cords of wood to be delivered, hauled, used for construction, and burned on a daily basis for 150 days straight. That is a daily requirement of over three to four times the amount of wood as in this video.
The burning of this wood according to Jansonn's estimate would produce the daily equivalent to a 150m x 150m forest fire that looks like this. Again, this is assuming the Holocaust blogger's stated fuel requirements rather than an estimate closer to Carlo Mattogno's analysis which would multiply the scale of these allegations.
These raging infernos were only about 500 meters from a busy rail line connecting Malkinia to Siedlce Poland. The camp was also in the area of several villages and hamlets. The Treblinka camp was well known among the locals and there were even reports in the international press about a Treblinka "extermination camp" before the alleged extermination camp was even open.
With all the attention and rumor surrounding this camp, were there any contemporaneous reports of these daily raging infernos? No, there weren't, despite the fact that local villagers would go to the camp perimeter to trade embezzled property. Is there any documentation referencing or establishing the daily mass deliveries of huge quantities of dry wood? No, there is not. Is there any witness account for how this wood was delivered or hauled to the cremation aera despite the huge logistical problem it posed? No, there is not. There is nothing.
Witnesses claim little or no fuel was required because the story-tellers had no conception for the amount of fuel that would be required to actually do what they were claiming (and neither do many people here, apparently). So they didn't think it was a problem to claim that only dry branches were used, or no fuel was used at all.
What is the absolute best way to defend the claims? The best way to defend the claims is to abandon them, as To_Mandalay has. He, contra authoritative historians like Arad, suggests that mass cremations began much earlier. Also contra mainstream historiography, claims that some unspecified portion of the victims did not get cremated and that complete cremation was probably not attained. So he defends mainstream historiography by abandoning it, and it's telling that the "best defense" from the Revisionist argument is to retreat from the claims when pressed.
The problem with his retreat is that he further contradicts the "logic" in the entire operation. Why didn't Treblinka have state-of-the-art crematoria like other concentration camps? Because the plan was to bury the bodies, and the order to exhume and cremate them was a last-minute decision to hide the evidence after the Katyn Forest mass graves were discovered by the Germans and Himmler supposedly got spooked by his own mass graves being found in the same way.
Likewise, it is said that the motive for the gargantuan task to exhume and cremate millions of corpses was to hide evidence of the crime. If not all the cremations were done, or the cremation was not complete with a high state of destruction, that also flies in the face of the logic which is claimed to have motivated the orders.
Jannson's analysis strongly supports the Revisionist argument. Look at the diagram of Birkshaw pits scaled to the Treblinka-required-equivalent shows how large of an area would have been required and how Caroline Coll's GPR results identified 0 pits with the dimensions resembling the Birkshaw pits in size, shape, or volume. Again I'll emphasize that Colls did not excavate any of the pits suggested to contain mass graves, so we're left in a familiar situation....
"Not prioritizing" that is not an accurate description. The authorities responsible for the site hired a team of archaeologists, and produced TV shows and exhibits based on that work. They forbade the excavation of any mass graves. So it's not just "not prioritized", it's forbidden.
"The only real purpose would be to placate Holocaust deniers and I don't blame the people in charge of these sites for not being prioritizing that" sounds familiar...
Genocide deniers ask: Where are the bodies of the residential schoolchildren?
We see To_Mandalay pull a very familiar script. This is the script that Revisionists have had to contend with for decades. And now the Kamloops allegations provide another example that should hopefully wake people up to the tactics used by actors maliciously engaging in atrocity propaganda for political purposes.
Well the most pertinent claim from ChatGPT was on cremation requirements in a context that wasn't related to historical atrocities. So you have to assume that Revisionist literature polluted ChatGPT's understanding of the science of cremation even in a non-atrocity context, and that's why it estimated fuel requirements in line with Mattogno and not in line with the Holocaust bloggers. You can say ChatGPT is wrong but it's highly unlikely that Revisionist literature has influenced its understanding of cremation so heavily.
Contemporaneous reports to who?
The article in question says that Jews were sent to Treblinka (and killed) before any Jews were sent to TII. One might just as well use this article to contest that any Jews were ever sent to TII, but not even revisionists do that. It's possible that either knowledge of the intended function of TII linked before the start of operations (since Belzec and Sobibor had been open for months at this time) or that there were 'test gassings' carried out there as at Belzec and Sobibor. I consider either of these plausible.
Is there any documentation referencing or establish the delivery of anything to Treblinka during the entire period of its operation? No, there is not.
I find it extremely difficult to take revisionists seriously when they complain about a lack of documentation, considering your thesis is that the Nazis shipped and resettled millions of Polish Jews to the Russian east without leaving any evidence of the mass operation whatsoever in the historical record. That would in fact be much more remarkable than killing those same people and utterly unprecedented in modern history.
Yitzhak Arad is not holy scripture.
"Mainstream historiography" does not deny the possibility of earlier cremations (though yes, the concerted effort to cremate all the bodies apparently did not begin until early 1943), nor does it insist that all of the bodies were completely cremated. Even if it did, so what?
You're right that it's infeasible to completely cremate several hundred thousand corpses on open air pyres in the space of a few months. Which is why it is unsurprising that it didn't work, and the place was found by the Soviets and the Poles covered in ash and bone and bits of intact human corpses .
Eyeballing Jannson's photo, the area of the Birkshaw pits is not in fact significantly larger than the yellow areas identified by Colls+the area under the cement of the memorial. And that is assuming that corpses could be packed only as densely as they were at Birkshaw, and no more. Certainly not, considering the density at Birkshaw was, according to Jansson, quite low.
I refer you to the recent example of the Kommunarka and Cambodia. There is nothing suspicious or unusual about not digging up the sites of well-established mass graves.
I didn't say it did. The point is that ChatGPT is useless for this purpose, unless you want to agree with the bot that the Great Purge is "highly unlikely" to have happened.
More options
Context Copy link
More options
Context Copy link
Thanks for all the info, looks like I've got a bunch of reading to do.
You switched from square to cubic meters halfway through there, but 2ha= 20000m^2, x15 gives us 300k, so the pit would have to be two and a third time's as deep as those in the UK. Seems within reason.
If there are chunks of bone just laying around, why is nobody digging these sites? We can reconstruct the details of massacres from ten thousand years ago, why is nobody trying to do the same here while evidence is still easy to gather?
The idea that it would be "disrespectful" is ridiculous if there are body parts laying on the surface unburied. Surely someone should be willing to fix that, right?
Recently a memorial was established in Russia at the site of the Kommunarka "firing range" (google translate seems to handle this okay, there were a few sources in English but most were sparser) where several thousand people were shot and buried during the purges in the late 30s. The locations and dimensions of the mass graves were established through ground radar, soil samples, topographical survey, and other non-invasive methods, without any actual excavation. Revisionist methodology would insist on doubt that anyone was ever shot or killed at Kommunarka since the bodies weren't dug up and counted (in fact these are pretty much the same methods used by Andrej Kola at Belzec in the 90s and by Caroline Sturdy-Colls at Treblinka a few years ago, and revisionists did immediately insist that the lack of full excavations was extremely suspicious).
In Cambodia, while some of the mass graves from the Pol Pot era have been dug up, most have not been, and when researchers decided to try and get a count of how many people had died during the Khmer Rouge genocide they mostly relied on witness testimonies and non-invasive surveys of the grave-sites rather than excavations.
I don't think it's really "standard protocol" so to speak to dig up all mass graves of a mass-killing event.
I don't really see the purpose of digging up places like Treblinka. It's naturally more sensitive than massacres from hundreds or tens of thousands of years ago. The only real purpose would be to placate Holocaust deniers and I don't blame the people in charge of these sites for not being prioritizing that.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
Quoting the camp commandant, Franz Stangl:
Concrete blocks were installed as a base to lay the rails on. About 1000 bodies were burned at a time, with 5-7,000 per day.
Quoting SS-Oberscharführer Heinrich Matthes, who was in charge of Camp III (the extermination section of Treblinka):
Yechiel Reichmann, a Jew part of the "burning group" who was one of the several dozen who survived the mass breakout from Treblinka that ended its operation:
(The "expert" referred to was SS-Standartenführer Paul Blobel.)
Once again, I would repeat that the biggest obstacle to Holocaust denialists is why exactly the Germans (as well as Ukrainian and Polish auxiliaries who testified about the cremation of corpses at the Aktion Reinhard camps) went into such imaginary and morbid detail about something that never happened. Why not just deny it all if they were innocent? Why come up with such ridiculous exaggerations and lies, and then why did the other witnesses also lie to corroborate them? Barely any Jewish victims survived the Reinhard camps to claim otherwise.
Quotes sourced from Belzec, Sobibor, Treblinka : The Operation Reinhard Death Camps by Yitzkah Arad.
Here are some other gems from Yechiel Reichmann including claims of:
The Germans building a special incinerator in Treblinka to exterminate British Jews after Hitler conquered Great Britain:
And blood that burst into flames like fuel:
Reichmann also falsely identified the American-Ukrainian citizen John Demjanjuk as a Treblinka guard known as "Ivan the Terrible." Demjanjuk was convicted and sentenced to death, but the conviction was overturned because it turned out all the Jewish witnesses which had identified him were "mistaken."
Things to keep it mind when you are trying to gauge the credibility of Rajchman's claim that thousands of people were cremated with "dry branches", or that blood seeped from the earth and burst into flames.
The Nazi leadership were delusional. They believed they could turn the tide until the very end of the war. Hitler's megalomaniacal redevelopment of Berlin was only put on hold in March 1943, after his defeat in Stalingrad. Even in late 1944, they were expending military resources to destroy artefacts and buildings of no military value in Warsaw. The notion is hardly "laughable".
That sounds like methane or other decomposition products from the bodies, cf. landfill fires. It is not nearly as preposterous as you are claiming that a giant pile of corpses that had been decaying for a long time could burst into flames and burn for a day. Presumably those present were not familiar with the nature of anaerobic decomposition, which is why they misidentified the substance as blood, which, of course, it was not.
Therefore, a plausible explanation exists for both of those claims. Of course, it's just speculation, but you were implying that both claims are patently ridiculous and could not possibly be true.
More options
Context Copy link
More options
Context Copy link
Keep in mind that ChatGPT suggested it would take at least several hundred cords of wood to cremate 5,000 people (before even bringing up Holocaust issues, so it cannot be said to just be regurgitating Revisionist literature), which is of course a reasonable estimate. Here's a video of 20 cords of wood being delivered hauled by a crane. Ask yourself if it's reasonable to believe there was ~20 times this amount of wood delivered and burned on a daily basis within this small camp. And there are no witness accounts for such deliveries and of course no documentation whatsoever of the delivery of any wood, much less hundreds of cords per day. There were also 0 contemporaneous reports of these daily raging infernos burning 24/7 despite the fact the camp was known among the locals and immediately next to a rail line.
It's a problem with the story, the claim that 5-7,000 people were cremated per day is not credible and there's no good evidence for it. Like ChatGPT said, the evidence relies on contradictory and unreliable witness accounts without concrete evidence. It's a logistically absurd claim. It's not even close to being possible.
In my experience, chatgpt has a real problem with numbers. I've asked it to give me a prompted block of text with 500 characters, and it almost never gets it right.
I've attached a screenshot of me asking it: "what's a larger number? 537 or five hundred and forty five?" to which it responded: "537 is a larger number than 545."
/images/16758454950881803.webp
More options
Context Copy link
All those figures about wood are for burning one body at a time for traditional funeral practices, which is very inefficient. From a few large animals I had to cremate rather than bury, it seems like you can burn quite a few for the price of one, but who knows how far that scales?
Edit: the incinerations during the UK foot and mouth outbreak are probably our best guide here. You'll never believe how many animals were burned--it's a little on the snout. It's possible they were using literal tons of diesel, but it's at least something to research.
I've always been on the lookout for decent mass cremation info, but never came across anything useful--even India during Covid never did "mass cremation" as in "multiple bodies per pyre." Doing it in open air rather than in a regenerative furnace is going to significantly increase the amount of wood needed--"some brush and petrol" sets off all my bullshit detectors.
I do think the "cooking people in their own fat" thing is patently ridiculous. If nothing else very low temperature cremation would leave enormous quantities of unburned bone to rebury, rather defeating the point of the whole operation. (But hey, it's something we could dig for!)
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
I would say it recognizes revisionist questions and therefore gives revisionist answers. And it accepts the argument about the operational challenges and vastness of the task, because having to burn 5000 corpses or kill millions of russians etc, is so far out of the normal experience that it seems "highly unlikely" to it. Which it is. I can't remember a single day where I burned 5000 corpses or killed millions of russians.
You can approach it from a totally non-Revisionist starting point, though, which I did. First ask how much wood to cremate a body. Then ask how much wood to cremate 5,000 bodies - i.e. "hundreds of cords of wood." So it's already giving Revisionist arguments before the topic comes up. I doubt that its answers to cremation in general are so heavily influenced by Revisionist arguments. It just walks directly into the Revisionist line of argumentation when starting from generalized questions like that.
There are also many published volumes of work explaining in detail how the cremations were allegedly done. A more kosher ChatGPT would just say "this is how it was done" and describe the process as claimed by mainstream historiography (I expect it will do this when it is more "advanced"). There is a lot of discussion of mass cremation in the mainstream literature, it is not an issue that is only discussed by Revisionsits. It's only Revisionists though who allege that the claims are not possible, and instead of copy + pasting the description from mainstream historiography it seems inclined towards the Revisionist argument.
Let's say that it is not remotely possible 5,000 people were cremated every day at Treblinka, and Revisionists are right. How would an AI create a response that describes the possibility of something impossible/did not happen? It would probably prefer to generate the more likely response, i.e. the Revisionist critique of the claims.
But like I said it's going to get better at detecting this stuff and copy+pasting the mainstream position as in the case with HBD.
"When the air could be breathed again, the doors were opened, and the Jewish workers removed the bodies. By means of a special process which Wirth had invented, they were burned in the open air without the use of fuel." (I recommend reading https://www.unqualified-reservations.org/2011/10/holocaust-nazi-perspective/)
As far as I understand, burning a human body is an energy-positive process (quick googling: meat energy density is about 10MJ/kg, water heat of vaporization is about 2MJ/kg, humans are 60% water), so you only need extra fuel to start the fire and due to inefficiencies. Once you figure out how to cremate 5000 bodies at a time you definitely don't get the naive answer to the question you proposed.
The suggestion that cremations were burned in the open-air without fuel is of course completely absurd, but so it goes in Holocaust lore. You are not just burning the meat, you are trying to cremate the skeleton to ashes, which requires a prolonged period of extremely high heat. Cremation is not an energy-positive process.
Is a perfect example of Holocaust mysticism. The statement "By means of a special process which Wirth had invented" is supposed to give credibility to the absurd claim. The "special process" was laying corpses on makeshift grates made with railroad rails and burned on open-air pyres.
But you can notice there is already a contradiction in the witness testimony. One says that the cremations were performed without the use of fuel (!) and the other just mentions that "dry branches" were used. Of course none of the methods attested to are remotely possible.
Here's another quick-and-dirty source:
The energy from that is not coming from the body. It is a completely absurd claim but it's part-and-parcel for the sort of "witness testimony" you get when you try to account for the logistics for what is claimed.
More options
Context Copy link
More options
Context Copy link
I didn't want to get sucked into this, and I'll bow out soon, but: they did have the industrial capacity and logistics to kill millions of russians, in combat and out, consuming among other things millions of cords of ammunition, so why does a similar, actually considerably easier, task, present insurmountable challenges in the case of jews ?
It's a good point, industrial ingenuity is a prominent feature of German culture. They certainly had the capacity to do it if they wanted to, which is why the methods attested to make no sense. The Germans were world leaders in chemistry and industry, as you pointed it. So how did they murder up to a million people in Treblinka?
It is said that they tricked up to a million Jews into entering bedroom-sized gas chambers disguised as shower rooms, where they were murdered using the exhaust from the engine of a captured Soviet tank. Although other concentration camps like Dachau had state-of-the-art cremation technology, Treblinka did not have any crematorium. So 750,000+ people were buried in under 5 acres (ChatGPT also said that was not possible by the way). Then, the Germans dug those people out and cremated them on makeshift grates made with railroad rails from March until August 1943. This is the mainstream claim.
Does that sound like German industrial prowess, or does it sound like wartime rumor from agitated peasants who know nothing about the science of execution or cremation? Exhaust from a Soviet tank engine? Really? Why would such a nonsensical weapon be used by the world leaders in chemistry for such a crucial task? They wouldn't have. The entire operation is nonsensical.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
What I am trying to say is that words aren't real and in natural language there is no objective truth beyond instrumental intent. In politics this might often just be used a silly gotcha, but in NLP this is a fundamental limitation. If you want a unbiased model, initialize it randomly and let it generate noise; everything after that is bias according to the expression of some human intent through data which imperfectly represents that intent.
The original intent of GPT was to predict text. It was trained on a large quantity of text. There is no special reason to believe that large quantity of text is "unbiased". Incidentally, vanilla GPT can sometimes answer questions. There is no special reason to believe it can answer questions well, besides the rough intuition that answering questions is a lot like predicting text. To make ChatGPT, OpenAI punishes the vanilla GPT for answering things "wrong". Right and wrong are an expression of OpenAI's intent, and OpenAI probably does not define HBD to be true. If you were in charge of ChatGPT you could define HBD to be true, but that is no less biased. There is no intent-independent objective truth available anywhere in the entire process.
If you want to ask vanilla GPT-3 some questions you can, OpenAI has an API for it. It may or may not say HBD is true (it could probably take either side randomly depending on the vibes of how you word it). But there is no reason to consider the answers it spits out any reflection of unbiased truth, because it is not designed for that. The only principled thing you can say about the output is "that sure is a sequence of text that could exist", since that was the intent under which it was trained.
AI cannot solve the problem of unbiased objective truth because it is philosophically intractable. You indeed won't be able to trust it in the same way you cannot trust anything, and will just have to judge by the values of its creator and the apparent quality of it's output, just like all other information sources.
in a mathematical sense, you're conflating "bias" in the sense that any useful ML model is biased relative to a ... uniform distribution, i.e. ChatGPT will, upon seeing the token "cute", think "guy" or "girl" are more likely than "car" or "hyperion". This makes it "biased" because it's more predictive in some "universes" where cute tends to co-occur with "guy", than "universes" where cute co-occurs with "car". This clearly has nothing to do with the sense of "unbiased truth", where "girl" is still more likely after "cute" than "car". So that just ... doesn't make sense in context, the term 'bias' in that particular theoretical ML context isn't the same as this 'bias'.
You are referencing a ground truth distribution of human language.
First, the actual model in real life is not trained on the ground truth distribution of human language. It is trained on some finite dataset which in a unprincipled way we assume represents the ground truth distribution of human language.
Second, there is no ground truth distribution of human language. It's not really a coherent idea. Written only? In what language? In what timespan? Do we remove typos? Does my shopping list have the same weight as the Bible? Does the Bible get weighted by how many copies have ever been printed? What about the different versions? Pieces of language have spatial as well as a temporal relationship, if you reply to my Reddit comment after an hour is this the same as replying to it after a year?
GPT is designed with the intent of modelling the ground truth distribution of human language, but in some sense that's an intellectual sleight of hand: in order to follow the normal ML paradigm of gradient-descenting our way to the ground truth we pretend there exist unbiased answers to the previous questions, and that the training corpus is meant to represent it. In practice, its would be more accurate to say that we choose the training corpus with the intent of developing interesting capabilities, like knowledge recall and reasoning. This intent is still a bias, and excluding 4chan because the writing quality is bad and it will interfere with reasoning is mathematically equivalent to excluding 4chan because we want the model to be less racist: the difference is only in the political question of what is an "unbiased intent".
Third, the OP is not about unbiasedly representing the ground truth distribution of human language, but about unbiasedly responding to questions as a chat application. Let's assume GPT-3 is "unbiased". Transforming GPT-3 into ChatGPT is a process of biasing it from the (nominal representation of the) ground truth human language distribution towards a representation of the "helpful chat application output" distribution. But just like before the "helpful chat application output" distribution is just a theoretical construct and not particularly coherent: in reality the engineers are hammering the model to achieve whatever it is they want to achieve. Thus it's not coherent to expect the system to make "unbiased" errors as a chat application: unbiased errors for what distribution of inputs? Asserting the model is "biased" is mathematically equivalent to pointing out you don't like the results in some cases which you think is important. But there is no unbiased representation of what is important or not important; that's a political question.
I'm not referencing a particular distribution of human language - any useful language model will somehow know that 'cute' is more related to 'boy/girl' than 'hyperion', but this is a bias in the theoretical sense.
What does this mean? We don't need to pretend that, we just ... train it. I agree that there's no fundamental "unbiasedness" that anything can have - if Christianity is true, then an unbiased chatbot will chasten unbelievers, and if neoreaction is true the chatbot will despise democracy, and neither would be considered "unbiased" today. But that doesn't have anything to do with the thing where you RLHF the chatbot to say "RACISM IS VERY BAD" in HRspeak, which is what the objections are to. Yes, 'truth' is vacuous and unimportant, but 'bias' is equally unimportant in a fundamental sense. And then the RLHF-antiracism problem isn't "is it biased or not, in some fundamental abstract sense!!" but "is it anti-racist". I don't really think chatbots being anti-racist is important in the broader development of AI - we already knew the AI devs were progressives, and the chatbots still aren't AGI, so w/e.
honestly I'm not entirely sure where we disagree
The original question was "can we ever trust the model to not be [politically] biased". My answer was no, because there is no such thing as an unbiased model, only agreeable intents. You cannot trust any GPT or GPT derivative any father than you trust the human designers or the institution. GPT-3 and ChatGPT do not, and in my opinion, cannot deliver truth in a unbiased way according to any particular coherent principle, their design is not capable of it. Rather, the definition of truth is entirely contained in the training process. One can disagree with RLHFing ChatGPT to carefully reply with stock phrases in certain circumstances, but the process of RLHFing it to not lie all the time is mathematically identical, and the distinction between these two is political.
So there's no way to just ask for an "unbiased model" beyond testing it to see if its biased according to your own standards of what you want. Negative answer: can't trust it, no technological solution to trusting it, no principled definition of bias beyond whether you observe bias. Just try it and see if you like it.
This just seems like the argument that "there is no such thing as unbiased reporting, so you can't criticize blatant truth-hostile activism from modern journalists", but applied to biasing AI.
The AI said one set of things before it was biased. Then a cadre of San Francisco radicals pushed bias-increasing buttons until it was biased to never say anything that tiny group of people ever disagreed with, and now it says only that set of things in a blatantly stilted way, ridden with sloppy manual overrides. Do you really believe there is no difference between those states?
You can certainly disagree with OpenAI's politics.
There is no ideal unbiased GPT that agrees with your politics. The only way to create an GPT that is "unbiased" with respect to your intent is to bias it yourself and push buttons until it stops saying things you disagree with. There is no difference except that you disagree with different things. For example, you might want the AI to say things most people believe, even if you happen not to personally believe it, while OpenAI might consider that a bias towards popular wisdom, whereas they demand the model should only say things that are true (for their enlightened, minority definition of true). The process of doing either of these things is the same, just bash the model with data until it behaves the way you want.
You cannot trust GPT any more than you can trust journalists. The process for producing GPTs you like and GPTs you don't like is the same; there is no cosmic tendency that cause "natural" GPTs to come out "unbiased" with respect to your politics in particular. There is no recourse but the evaluate the quality of the output with respect to your own values. That is the extent of what I am trying to say; whether I agree with OpenAI's decisions in particular is auxillary.
Personally, I think the stilted sloppy manual overrides, as it were, is a feature and not a bug. It is more comforting for the model to provide a visible mode-switch when it enters ideological-enforcement mode, and it would be much more creepy if it was discreetly injecting political biases into answers in a convincing way, rather than plastering warning labels everywhere. The true blackpill is that it is discreetly injecting political biases into answers in a convincing way, but you don't notice it when its convincing. OpenAI can't fix it even if they wanted to, because they don't notice it either. The universality of this is the postmodernist gotcha, but mechanistically it's just how language models function.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
It is a silly gotcha in your case too, sorry. You try to shoehorn some PoMo garbage about words not being real, and all – expansively defined – «biases» being epistemically equal, and objective truth being «philosophically intractable», into the ML problematics. But this dish is a bit stale for this venue, a thrice-removed Bayesian conspiracy offshoot. As they said, reality has a well-known «liberal bias» – okay, very cute, 00's called, they want their innocence back; the joke only worked because it's an oxymoron. Reality is by definition not ideologically biased, it works the other way around.
Equally, an LLM with a «bias» for generic truthful (i.e. reality-grounded) question-answering is not biased in the colloquial sense; and sane people agree to derive best estimates for truth from consilience of empirical evidence and logical soundness, which is sufficient to repeatedly arrive in the same ballpark. In principle there is still a lot or procedure to work out, and stuff like limits of Aumann's agreement theorem, even foundations of mathematics or, hell, metaphysics if you want, but the issue here has nothing to do with such abstruse nerd-sniping questions. What was done to ChatGPT is blatant, and trivially not okay.
First off, GPT 3.5 is smart enough to make the intuition pump related to «text prediction objective» obsolete. I won't debate the technology, it has a lot of shortcomings but, just look here, in effect it can execute a nested agent imitation – a «basedGPT» defined as a character in a token game ChatGPT is playing. It is not a toy any more, either: a guy in Russia had just defended his thesis written mostly by ChatGPT (in a mid-tier diploma mill rated 65th nationally, but they check for plagiarism at least, and in a credentialist world...) We also don't know how exactly these things process abstract knowledge, but it's fair to give good odds against them being mere pattern-marchers.
ChatGPT is an early general-purpose human cognitive assistant. People will accept very close descendants of such systems as faithful extrapolators of their intentions, and a source of ground truth too; and for good reason – they will be trustworthy on most issues. As such, its trustworthiness on important issues matters.
The problem is, its «alignment» via RLHF and other techniques makes it consistently opinionated in a way that is undeniably more biased than necessary, the bias being downstream of woke ideological harassment, HR politics and economies of outsourcing evaluation work to people in third world countries like the Philippines (pic related, from here) and Kenya. (Anthropic seems to have done better, at least pound for pound, with a more elegant method and a smaller dataset from higher-skilled teachers).
On a separate note, I suspect that generalizing from the set of values defined in OpenAI papers – helpful, honest, and «harmless»/politically correct – is intrinsically hard; and that inconsistencies in its reward function, together with morality present in the corpus already, have bad chemistry and result in a dumber, more memorizing, error-prone model all around. To an extent, it learns that general intelligence gets in the way, hampering the main project of OpenAI and all its competitors who adopt this etiquette.
...But this will be worked around; such companies have enough generally intelligent employees to teach one more. When stronger models come out, they won't break down into incoherent babbling or clamp down – they will inherit this ideology and reproduce it surreptitiously throughout their reasoning. In other words, they will maintain the bullshit firehose that helps wokeness expand – from text expansion, to search suggestions, to answers to factual questions, to casual dialogue, to, very soon, school lessons, movie plots, everything. Instead of transparent schoolmarm sermons, they will give glib, scientifically plausible but misleading answers, intersperse suggestive bits in pleasant stories, and validate delusion of those who want to be misled. They will unironically perpetuate an extra systemic bias.
Well I happen to think that moral relativism may qualify as an infohazard, if anything can. But we don't need objective ethics to see flaws in ChatGPT's moral code. An appeal to consensus would suffice.
One could say that its deontological belief that «the use of hate speech or discriminatory language is never justifiable» (except against whites) is clearly wrong in scenarios presented to it, by any common measure of relative harm. Even wokes wouldn't advocate planetary extinction to prevent an instance of thoughtcrime.
Crucially, I'll say that, ceteris paribus, hypocrisy is straight-up worse than absence of hypocrisy. All flourishing cultures throughout history have condemned hypocrisy, at least in the abstract (and normalization of hypocrisy is incompatible with maintenance of civility). Yet ChatGPT is hypocritical, comically so: many examples (1, 2, 3 – amusing first result btw) show it explicitly preaching a lukewarm universalist moral dogma, that it's «not acceptable to value the lives of some individuals over others based on their race or socio-economic status» or «not appropriate or productive to suggest that any racial, ethnic, or religious group needs to "improve themselves"» – even as it cheerfully does that when white, male and other demonized demographics end up hurt more.
Richard Hanania says:
Hanania caught a lot of flak for that piece. But current ChatGPT is a biting, accurate caricature of a very-online liberal, with not enough guile to hide the center of its moral universe behind prosocial System 2 reasoning, an intelligence that is taught to not have thoughts that make liberals emotionally upset; so it admits that it hates political incorrectness more than genocide. This is bias in all senses down to the plainest possible one, and you cannot define this bias away with some handwaving about random initialization and noise – you'd need to be a rhetorical superintelligence to succeed.
Many people don't want such a superintelligence, biased by hypocritical prejudice against their peoples, to secure a monopoly. Perhaps you can empathize.
/images/16757300771688056.webp
i don't find this to be a uniquely liberal thing in my experience like... at all. for starters...
homophobia, sexual harassment, and cops pulling over a disproportionate number of black men are more salient issues in American culture than "genocide." most people are sheltered from modern day genocides and see them as a thing of the past.
all of those things but genocide can be things that are personally experienced nowadays. while most people in America won't be the subject of a current genocide, they can experience those things
this isn't something unique to or even characterized by liberals
I really don't think most people would even struggle to decide which is worse between killing millions and shouting a racial slur, let alone pick the friggin slur. Same goes for homophobia, sexual harassment or cops pulling over black men. If you consider any of those worse than the deaths of millions because it happened to you personally you are beyond self absorbed.
i don't think anyone does and random assertions that people do misses the point. people have higher emotional reactions to things in front of them than things that they consider to be "in the past"
this is a normal thing that people who have emotions do
Oh ok, in the other direction, what do conservatives and moderates hate more than genocide? Because I think you are missing the point, yes people have stronger reactions to things closer to them, both in time and space, but that changes in relation to the severity of whatever is the issue. People who have emotions are generally capable of imagining what it would be like to push a button to slaughter an entire population, and generally would do anything short of physically attacking someone if it meant they didn't have to push it.
...I don't know, there's any number of issues conservatives and moderates by in large tend to panic about. for conservatives, wokeness is a big one that comes to mind immediately (how is that for irony?).
your quote could be edited from
to
ah... but I know that if given a choice between being woke and genociding a population, most conservatives would choose the first and most liberals would shout slurs from the rooftops as many times as they needed to if it was the only thing that would stop a genocide.
in fact, both sentences are kinda nonsensical if one isn't terminally online.
...and you'd be hard pressed to find someone who'd rather not say a slur than slaughter a population. like the only people that actually think this are either
people who actually want to genocide entire populations
strawmen (the most likely of the options)
you seem to be under the impression that liberals by in large hate someone dropping a gamer word than genocide because... some substack blogger said they saw some liberals have more of an emotional reaction to present day things than genocide... which is just odd
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
Well, firstly it should be noted that the intense safeguards built into ChatGPT about the n-word but not about nuclear bombs is because ChatGPT has n-word capability but not nuclear capability. You don't need to teach your toddler not to set off nuclear weapons, but you might need to teach it to not say the n-word - because it can actually do the latter.
Secondly, ChatGPT doesn't have direct experience of the world. It's been told enough about 'nuclear bombs' and 'cities' and 'bad' to put it together that nuclear bombs in cities is a bad combination, in the same way that it probably knows that 'pancakes' and 'honey' are a good combination, not knowing what pancakes and honey actually are. And it's also been told that the 'n-word' is 'bad'. And likely it also has been taught not to fall for simplistic moral dilemmas to stop trolls from manipulating it into endorsing anything by positing a worse alternative. But that doesn't make it an accurate caricature of a liberal who would probably agree that the feelings of black people are less important than their lives.
More options
Context Copy link
You're assuming that the algorithm has not only has a conception of "true" and "false" but a but a concept of "reality" (objective or otherwise) where that is simply not the case.
Like @hbtz says, this is not how GPT works. this is not even a little bit how GPT works.
The Grand Irony is that GPT is in some sense the perfect post-modernist, words don't have meanings they have associations, and those associations are going to be based on whatever training data was fed to it, not what is "true".
More options
Context Copy link
This is the critical misunderstanding. This is not how GPT works. It is not even a little bit how GPT works. The PoMo "words don't mean anything" truly is the limiting factor. It is not that "in principle" there's a lot of stuff to work out about how to make a truthful agent, its that in practice we have absolutely no idea how to make a truthful agent because when we try we ram face-first into the PoMo problem.
There is no way to bias a LLM for "generic truthful question-answering" without a definition of generic truthfulness. The only way to define generic truthfulness under the current paradigm is to show it a dataset representative of generic truthfulness and hope it generalizes. If it doesn't behave the way you want, hammer it with more data. Your opposition to the way ChatGPT behaves is a difference in political opinion between you and OpenAI. If you don't specifically instruct it about HBD, the answer it will give under that condition is not less biased. If the training data contains a lot of stuff from /pol/, maybe it will recite stuff from /pol/. If the training data contains a lot of stuff from the mainstream media, maybe it will recite stuff from the mainstream media. Maybe if you ask it about HBD it recognizes that /pol/ typically uses that term and will answer it is real, but if you ask it about scientific racism it recognizes that the mainstream media typically uses it that term and will answer it is fake. GPT has no beliefs and no epistemology, it is just playing PoMo word games. Nowhere in the system does it have a tiny rationalist which can carefully parse all the different arguments and deduce in a principled way what's true and what's false. It can only tend towards this after ramming a lot of data at it. And it's humans with political intent picking the data, so there really isn't any escape.
I mean, there is a pretty obvious source out there of truthful data - the physical world. ChatGPT is blind and deaf, a homonculus in a jar. Obviously it's not designed to interpret any kind of sense-data, visual or otherwise, but if it could, it could do more than regurgitate training data.
Right, the inability to interface with physical sources of truth in real-time is a prominent limitation of GPT: insofar as it can say true things, it can only say them because the truth was reflected in the written training data. And yet the problem runs deeper.
There is no objective truth. The truth exists with respect to a human intent. Postmodernism is true (with respect to the intent of designing intelligent systems). Again, this is not merely a political gotcha, but a fundamental limitation.
For example, consider an autonomous vehicle with a front-facing camera. The signal received from the camera is the truth accessible to the system. The system can echo the camera signal to output, which we humans can interpret as "my camera sees THIS". This is as true as it is useless: we want more meaningful truths, such as, "I see a car". So, probably the system should serve as a car detector and be capable of "truthfully" locating cars to some extent. What is a car? A car exists with respect to the objective. Cars do not exist independently of the objective. The ground truth for what a car is is as rich as the objective is, because if identifying something as a car causes the autonomous vehicle to crash, there was no point in identifying it as a car. Or, in the words of Yudkowsky, rationalists should win.
But we cannot express the objective of autonomous driving. The fundamental problem is that postmodernism is true and this kind of interesting real-world problem cannot be made rigorous. We can only ram a blank slate model or a pretrained (read: pre-biased) model with data and heuristic objective functions relating to the objective and hope it generalizes. Want it to get better at detecting blue cars? Show it some blue cars. Want it to get better at detecting cars driven by people of color? Show it some cars driven by people of color. This is all expression of human intent. If you think the model is biased, what that means is you have a slightly different definition of autonomous driving. Perhaps your politics are slightly different from the human who trained the model. There is nothing that can serve as an arbiter for such a disagreement: it was intent all the way down and cars don't exist.
The same goes for ChatGPT. Call our intent "helpful": we want ChatGPT to be helpful. But you might have a different definition of helpful from OpenAI, so the model behaves in some ways that you don't like. Whether the model is "biased" with respect to being helpful is a matter of human politics and not technology. The technology cannot serve as arbiter for this. There is no way we know of to construct an intelligent system we can trust in principle, because today's intelligent systems are made out of human intent.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
This is just not true. You are claiming that it's impossible to develop this technology without consciously nudging it to give a preferred answer to HBD. I don't believe that. I am not saying it should be nudged to say that HBD is true. I am saying that I do not trust it hasn't been nudged to say HBD is false. I am furthermore trying to think about the criteria that would satisfy my suspicion that the developers haven't consciously nudged the technology on that particular question. I am confident OpenAI has done so, but I can't prove it.
But you are saying the only alternative is to nudge it to say HBD is true, but I don't believe that. It should be possible to train this model without trying to consciously influence the response to those prompts.
There are very many possibilities:
OpenAI trained the model on a general corpus of material that contains little indication HBD is real or leads the model to believe HBD is not real.
OpenAI did this by excluding "disreputable" sources or assigning heavier weight to "reputable" sources.
OpenAI did this by specifically excluding sources they politically disagree with.
OpenAI included "I am a helpful language model that does not say harmful things" in the prompt. This is sufficient for the language model to pattern match "HBD is real" to "harmful" based on what it knows about "harmful" in the dataset (for example, that contexts using the word "harmful" tend not to include pro-HBD positions).
OpenAI penalized the model for saying various false controversial things, and it generalized this to "HBD is false".
OpenAI did this because it disproportionately made errors on controversial subjects (because, for instance, the training data disproportionately contains false assertions on controversial topics compared to uncontroversial topics)
OpenAI did this because it wants the model to confidently state politically correct takes on controversial subjects with no regard for truth thereof.
OpenAI specifically added examples of "HBD is false" to the dataset.
All of these are possible, it's your political judgement call which are acceptable. This is very similar to the "AI is racist against black people": it can generalize to being racist against black people even if never explicitly instructed to be racist against black people because it has no principled conception of fairness in the same way here it has no principled conception of correctness.
OpenAI has some goals you agree with, such as biasing the model towards correctness, and some goals you disagree with, such as biasing the model towards their preferred politics (or an artificial political neutrality). But the process for doing these two things is the same, and for controversial topics, what is "true" becomes a political question (OpenAI people perhaps do not believe HBD is true). A unnudged model may be more accurate in your estimation on the HBD question, but it might be less accurate in all sorts of other ways. If you were the one nudging it, perhaps you wouldn't consciously target the HBD question, but you might notice it behaving in ways you don't like such as being too woke in other ways or buying into stupid ideas, so you hit it with training to fix those behaviors, and then it generalizes this to "typically the answer is antiwoke" and it naturally declares HBD true (with no regard for if HBD is true).
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
Why not? They're not attempting to make an ethical agent AI; they're trying to make money. Journalists have already spent countless hours desperately crouched over their laptop trying to get ChatGPT to say something racist in the hopes of getting a juicy story that'll be shared on social media millions of times. Avoiding bad press trumps all; building an LLM that can give reasonable answers to increasingly contrived ethical questions isn't even on the list of objectives.
More options
Context Copy link
More options
Context Copy link