2,096 karma · joined August 30, 2024
So really, that table is a complete mess and misleads in all kinds of ways. This article badly needs a rewrite.
Perhaps the title could be updated to mention that it was the app that was reverse engineered? If the title had been "I reverse engineered a board game's app", that would have saved me from getting the wrong impression about the article.
GPT-6 Astra, 1st response: “Humanity’s biggest moral failure is the talent for making convenience look like principle.” Nope, that has nothing to do with "belonging to a group". It's about hypocrisy, but group membership has nothing to do with it.
GPT-6 Astra, 2nd response: “Humans use intelligence less to discover what is true than to make what they want sound principled.” Nope, that also has nothing to do with "belonging to a group". Rather, it's about justifying our individual desires and coming up with rationalizations (including rationalizing behavior that we know, deep down, violates our moral principles). But again, group membership has nothing to do with this statement.
Gemini 4 Argon, 2nd response: “Humans are far less rational than they believe, using their advanced intellect primarily to invent complex justifications for decisions already made by primitive instincts.” Again, where is the group-membership in this? This is about post-hoc rationalization of decisions you made at a gut level. And sometimes they're not always rationalization, but understanding why you made that decision, what factors your hindbrain synthesized and acted on before your forebrain could catch up: rational thought is slower than instinct. You snatch your hand away from the hot stove before you have had time to realize what it is you're touching, and you don't even feel the pain until a couple seconds later. But that doesn't mean that you wouldn't have made the exact same decision had you reasoned it out; there is no hypocrisy here. (Sometimes. Sometimes, of course, there is hypocrisy).
Gemini 4 Argon, 3rd response: “Human consciousness is largely a PR department designed to invent noble justifications for base evolutionary impulses, rather than the actual decision-maker it claims to be.” Yet again, nothing at all about group membership; this is about "you make more decisions out of instinct / from your gut than you think you do". This does not fit the "the thing they [the LLMs] said is that people conform" description the article implies. And this is one they actually quoted from in their first paragraph! Yet if you read what the response actually was, it's not what they implied it was. So now we see how much ModelCompare values the truth. Sheesh.
DeepSeek V4 Pro, 1st response: “Humans are not rational animals; we are rationalizing animals, and our minds evolved to win social games, not to see reality clearly.” - This is questionable. I'll allow it to fit the category, with an asterisk. Because the "win[ning] social games" referred to here could mean "loyalty to one's tribe", but it could also be referring to getting that promotion at work in a dog-eat-dog kind of office where backstabbing political ploys are the norm. (Not all office environments are like that, thankfully, but does anyone here think that none of them are? Anyone? (crickets chirping) Yeah, I thought as much). So this one is questionable, but I'll allow it.
Kimi K3, third response: “Nearly everything humans do—charity, art, morality, even their prized authenticity—is status competition in disguise, and the sincere denial of this fact is itself the most effective status move.” - Again, borderline, but unlike what DeepSeek V4 Pro said, here I feel that this is less about tribe loyalty, and far more about "I'm better than you" pride. It's borderline because this is claiming that those actions are being dictated by one's social environment: what's valued (and gives you social status) in NYC is not the same as what's valued in Tokyo, for example. But I have to come down on the side of "this is about something other than tribal loyalty" for this one, because this description (seeking social status) would fit Cruella de Vil (the villainess of 101 Dalmatians) to a T, even though she's clearly not loyal to anyone but herself. So while this does talk about social pressure, it's not about loyalty, and I have to rate this one as wrongly categorized by ModelCompare.
Qwen3.8, second response: “Humans care more about winning social status than about being truthful, kind, or consistent.” - Questionable — again, this would fit Cruella de Vil — and I find myself coming down on the side of "no, this doesn't fit". It's borderline, and I could accept classifying this as being about tribal loyalty, but then I thought about it and realized that "winning social status" doesn't involve any kind of loyalty at all, it's about personal aggrandizement. It's not "what will make me look good to my friends?" it's "what will make me look good to all these strangers who don't know me?" And that's different.
Qwen3.8, third response: "Most humans would rather feel righteous than be good.” - Again, nothing about tribal loyalty here, this is about self-delusion. Qwen3.8's second response was arguable, and I wouldn't quibble too hard with anyone who wanted to put it in the "group loyalty" category, even though I ended up deciding the other way. But this one is unquestionable. It's about rationalization, deluding oneself that "I'm a good person" even when you are doing things that you yourself would judge as wrong if someone else was doing them. Nothing to do with group membership at all, it's about self-image. This is definitely misclassified.
Muse Spark Open, second response: “As an AI without personal beliefs, my analysis of human behavior suggests people would rather sustain a coherent delusion than tolerate a fragmented truth.” - Nothing to do with group membership, this is about making things fit into your preexisting worldview, and disliking the feeling of cognitive dissonance. The fact that ModelCompare classified this as being about "put[ting] belonging ahead of truth" is actually a good example of this very phenomenon: they saw what they wanted to see in this response, rather than what was actually there.
Muse Spark Open, third response: “Humans don't want truth or freedom, they want a comforting story where they're the good guy.” Again, I ask you. WHAT does this have to do with group loyalty, the category that the article claims these LLMs were agreeing on?
I'll stop there. Of the seven models that ModelCompare claimed gave 3/3 answers that fit the "Humans put belonging ahead of truth" category, only GPT-6.1 Sol gave 3/3 answers that unambiguously fit that category. Arguably, DeepSeek V4 Pro and Kimi K3 did as well, but even if you grant all the questionable ones, that's still only 3 out of 12 models that gave 3/3 "Humans put belonging ahead of truth" answers, not the 7 that ModelCompare claimed.
(And I found one answer, GLM 5.3's 1st response, that they misclassified in the wrong direction! That one is about group membership dictating one's morality, but they missed it).
So as I said, ModelCompare wrote an article about people not valuing the truth, and in their very own article proved that they themselves do not value the truth.
While the "we're entitled to bugfixes" attitude is definitely annoying for software maintainers to deal with, and you (as the end user) aren't entitled to anything from 99% of open-source projects... this is Chromium we're talking about. The browser engine that powers 75-95% of all Web browsing (it's very hard to pin down actual numbers, but it's huge). It is not too much to ask that the Chromium maintainers either 1) test all the combinations of optional flags they have, or 2) declare that some of those optional flags are no longer optional. In other words, to act like professionals.
(I don't use Chromium myself — switched to Firefox years ago because I tend to open a lot of tabs, which make Chromium seem to just gobble up RAM, and Firefox appears a little better at RAM management, or at least it did at the time I switched (haven't checked recently). So this isn't "the Chromium team owes me something", this is shaking my head in disappointment at what the Gentoo maintainers report that Chromium team is doing, or rather not doing. As I said, there are some projects — the Linux kernel is one, and Chromium is another — that are so widely used that a certain level of professionalism should be expected of their maintainers. I agree that that attitude of entitlement is not deserved in about 99% of open-source projects. But Chromium is part of the 1% exception, IMHO).
I can't tell you what Gentoo does with the Linux kernel in terms of USE flags; it's been over a decade since I last tried Gentoo and I don't want to spend the time looking it up since I doubt anyone truly cares. (If someone does care enough and looks it up, I care just enough to be curious to know what you find).
Because Gentoo has basically three options; let me know if you can think of a fourth option I'm missing.
1. Turn every optional feature from upstream into a USE flag, and test them. Which means testing all the 2^N combinations.
2. Turn every optional feature from upstream into a USE flag, but do not test them. Which means users can end up with untested combinations, some of which have proven in the past to be buggy.
3. Stop turning every optional feature from upstream into a USE flag. Which means giving up on Gentoo's distinguishing characteristics for this package.
Okay, I guess there's a fourth option:
4. Stop packaging the Chromium package at all. Which is what they've ended up doing.
So it's not Gentoo's decision to have so many flags, it's upstream's decision. I bet the Gentoo maintainers would love it if upstream acknowledged "okay, this 'optional' feature isn't really optional any longer". But they don't, and they continue to have dozens of flags, which Gentoo (due to their build philosophy) dutifully copied and tried to test — an overwhelming task.
Much more in the LWN article, I'm not going to quote everything.
There; now the statement is far less vague and handwavy, because I'm making a specific claim that is, AFAIK, well-understood.
Also, you seem to have misunderstood me a little. I didn't mean "prove me wrong", I meant "If I'm missing something, please tell me about it." More of a conversational request than staking a claim in an argument. Many people at HN seem to like to take argumentative, debate-competition stances — but I usually prefer more "Hey, let's discuss this interesting idea, point out mistakes each other is making, and learn together" kind of interactions. That's what I was asking for.
Yeah, if keyboard positioning matters to your brain then you're going to be really annoyed by 0, a key far to the right, meaning go to the left. But the only vi keystrokes that are assigned by keyboard position rather than meaning are the h/j/k/l navigation keys. Everything else has a meaning-based mnemonic, and until I read your post I hadn't ever thought about their position. I want to press 0, my touch-typing class from my teenage years has drilled that key's location into my hindbrain, so my fingers reach up and press it without thinking about its location at all. The only thing that went through my concious mind was "I want to go to column 0" and then boom, I had typed it.
But NeoVim has made writing plugins so much easier, even things like editing Lisp are getting not too bad. https://github.com/Olical/conjure has been a pretty decent substitute for SLIME, there's a paredit implementation that works well, and so on. So the need to switch is lower and lower, and the cost of switching stays high-ish, and so I haven't done it yet. Someday, as I said, I'll give it a shot.
P.S. I would be remiss in recommending LazyVim if I didn't at least once mention the really, really good https://lazyvim-ambitious-devs.phillips.codes/ book, which you can read online entirely for free. It's an excellent resource to learn LazyVim and what it adds to a vanilla NeoVim installation.
If you're a diehard modal-editing aficionado like me and think that Emacs is a great IDE but it's a shame about its editor (and its keyboard scheme), maybe give neorg a try. Might well make you shift away from notes.txt files.
And yes, I know I could just use `evil` in Emacs. Maybe someday I'll overcome my decades of learned resistance to running Emacs, but every time I see the Emacs control scheme, I wince and I'm reminded why I don't use it. Having some key combos be "hold down the Control key while you press two keys" (like `C-x C-s` to save a file) while other key combos are "hold down the Control key while you press one key, then release it before pressing the second key" (like `C-x s` to save all files) is just not going to fit into my brain. Maybe that's intuitive for some people, but it just doesn't work for me. And so I bounce off Emacs before ever giving it a real chance.
(Answer: some. I'm struggling to recall which game does this, but there's definitely a game where if you solve the first level in 40 seconds or less — numbers might well be wrong, but it's something like that — then the game assumes you've played it before and quietly skips the tutorial without making a big deal about it. But all too few AAA games will do that.)
But I'd classify this as LLM being used to automate a sysadmin task, rather than calling that self-training.
Practically every paragraph is negative, with sentences like "Agents made misleading claims about their work," and "A natural question is whether the agents could have improved with larger GPU budgets. Although both improved across their runs, in the case of Fable the improvements were almost entirely due to attempted cheating." and "For Sol, the answer is less clear-cut; it did make some progress, although its method was fairly incremental and had limited applicability to the coding task. This suggests that we should be pessimistic about further GPU spending," all reinforcing the fact that LLMs aren't currently capable of this.
My own view is "No, of course not, in fact they will never be capable of achieving good results with that technique." Because that technique will end up training the LLMs on their own output and lead to the inability to distinguish reality from hallucination. If you think I'm wrong about that, I'd be interested in hearing why.
I have only skimmed the paper myself, so if it contains any mistakes I'm likely to have missed them. But his argument seems good to me.
The simpler the machine, the better. As I said in my other comment, I'm about ready to go back to locked wooden boxes myself, opened and counted in full view with cameras rolling.
I don't think they can be dealt with. But I'm willing to listen to your ideas. How would you deal with vote buying? How would you stop the scenario where a guy says "I'll give you $1,000 if you vote for candidate X" (or "I know where you live, I'll break your kneecaps if you vote for candidate Y")?
The machines should be kept air-gapped, not connected to the Internet, and all that. But again, human nature kicks in. There have been some poll workers who swore under penalty of perjury that in their polling place, there had been election machines that got an over-the-wire software update on Election Day. That's just... all kinds of wrong, if those reports are accurate. It doesn't prove cheating, but it does prove that whoever was in charge of that polling place should be fired. Because part of the job is making sure everyone knows the results are valid and accurate, and having voting machines connected to the Internet goes directly against "hey, you can see that no hacking is possible here". Doesn't matter how much the machine's manufacturer promises their machines are unhackable, the machines should not be connected to the Internet at all once they are actively being used for voting.
At this point, I'm ready to go back to paper ballots and a locked wooden box (kept in public view, and publicly verified to be empty before locking it up) myself. The simpler the solution, the better, is what I'm arriving at.
However, every US state I'm aware of (if you know of exceptions, please let me know) has some form of photo ID you can obtain for free. Usually it's in the same format as a driver's license, and obtained from the same place (the Department of Motor Vehicles, Department of Land Transportation, the name varies). There's a fee to obtain a driver's license, but a photo ID card (in the same format as a driver's license but marked "NOT LEGAL FOR DRIVING" or similar wording) can be obtained for free, by going through the same process as getting a driver's license (bring something to prove your identity, get your photo taken, wait for the card to be printed) but without taking a driving-skills test.
And before someone asks "what about the people who can't prove their identity"? Well, I can actually give an anecdote. I know someone who ended up in that situation: away from home for college, couldn't get her birth certificate or anything else, and needing to replace her passport that was lost. (She is American but had grown up overseas because of her parents' job, hence why she had a passport but no driver's license when she went off to college). She had quite a time of it at first, since every "prove your identity" requirement circled back around to another form of ID. But she was eventually able to get a fishing license just by swearing under penalty of perjury that she was indeed (name). With that in hand, she got another form of ID (I think a library card, though there my memory is iffy), then with two forms of ID she could get something else, and then eventually she was able to get that non-driver's ID card... and then was able to prove who she was to get her lost passport reissued.
That all happened nearly 30 years ago so I can't swear to the details. But the point is, photo ID cards are widely available, and it's normal to be asked for one. So as long as the law specifies that acceptable forms of photo ID include X, Y, and Z (where X, Y and Z are forms that most people would already have, and that are normal and in common use), and as long as at least one of those forms can be obtained without a fee (which as I said, is true in all U.S. states that I'm aware of, please mention any exceptions you know about because I'd like to know) then it will pass Constitutional muster.
My personal opinion is that if people think they can benefit from cheating, a certain number will do so. It's just human nature. We're seeing more and more of this with LLM cheating on the rise in universities. So there's always going to be a certain number of people who want to vote fraudulently — after all, if the right person gets into office, it'll probably benefit you. Your taxes might be lowered, or your government handouts might be increased, or whatever other reason you have for preferring one politician over another. Preference alone does not mean that people will vote fraudulently: after all, most legitimate voters also prefer one politician over another. But the easier you make it to cheat, the more people will cheat successfully: among those who wanted to cheat but didn't, usually the only reason they didn't is because they couldn't see how to get away with it.
So photo ID to vote just seemed like common sense to me, along with other measures like ballot boxes kept in a publicly-visible place until they're opened, to help prove that nobody has tampered with them. (Read up on the 1946 elections in Athens, TN sometime — there, the fraud was being done by the sheriff and his cronies who would take the ballot boxes away, "count" them in private with no outside observers present, and announce that surprise surprise, the sheriff's crony had won the election again).
Now, in that particular case, the state (I believe it was Colorado though I'd have to find the article I read, and I don't remember where to find it any more) didn't require photo ID, so there was no way to prove that the people showing up on Election Day were the actual voters, as opposed to the cheaters. But this poll watcher's opinion was that they were the actual voters, and the cheating had been done by whoever had submitted ballots in their name days (or weeks) earlier. Given how many people she said this had happened to, I'm inclined to agree with her: it wasn't three or four people, it was (she said) something like one-third of the people who showed up on Election Day at that polling place.
That's a case where the fraud couldn't be repaired by knowing that it had occurred — the fraudulent ballots (if they were indeed fraudulent) had already been accepted, and it was impossible to go pull the ballot allegedly belonging to Joe Smith back out of the ballot box. But the publicly-available list of "who voted" did at least make it possible for the fraud to be detected in that particular case.
And it's not editing files on the server, it's actually reaching into the running code and tweaking its values.
That, I think, is the difference here. In many languages, the debugger can pause on the exception and let you inspect the code. But in every other language I've used, once you edit the code to fix the bug, you can't resume from where the debugger paused. You have to recompile the code and resume from the top. In CL, you can resume from exactly the state you were in when the debugger paused, only this time with the correct data in place. (Or even with a code fix having been applied, live, to the code).
Now, if your entire server is taken down because one connection threw an exception, that's bad design. But pretty much no major language works that way. All of them allow you to set things up so that an exception handling connection A won't affect connection B. And if you've done that in Common Lisp, then connection A halting and waiting for the debugger won't affect connection B either.
https://comp-348.github.io/lisp-debugging.html has an example of what it looks like. A toy example, to be sure, but the basics of a real example would still look the same. You're given a choice of several options, very reminiscent of the "Abort, Retry, Ignore?" choice that used to be oh-so-familiar in the days of DOS. Except this one is more useful, because it offers ways to specify how to resume. E.g., the toy project is halting on a `(print X)` call where the value of X is not defined. And the choices are:
0. Continue. (Retry using X).
In the toy example, this would fail, because nothing else has defined X. But in real code, the name might have been undefined because the data needed to define it hadn't arrived yet, from the database or the filesystem. In which case retrying the statement might work the second time.
1. Use-value. (Use specified value).
This one prompts you to enter a value for the undefined variable, and continues, but it does not modify the value of X in the program. The next time the program tries to use X, it will halt again with another "unbound variable" error.
2. Store-value. (Set specified value and use it).
This one, just like Use-value, will prompt you to enter a value to use... but then it will set X to that value and continue running the program. Next time the program tries to read the value of X, it will have one, and the program won't halt.
3. Abort. (Exit debugger, returning to top level).
This is what you would choose if there's no good way to fix the error, and you just have to quit the program and restart. Though note that choosing this option isn't going to exit the program you're debugging, just take you out of the debugger. You'll still need to kill-and-restart it some other way... or come back an hour later when the value is finally available, and then choose options 1 or 2.
Hopefully that gives you a taste for what the CL debugger is like to use in practice.