A year ago (or so) I had a colleague whose messages were all obviously AI-generated. I told them that it felt weird that they were sending me AI answers in Slack and code reviews, and they stopped doing it.
Not an interesting story, just wanted to share that the other party might not be aware of how this comes across on the people that have to read their AI messages.
Sure, but I don't think they must be mutually exclusive; on the contrary: in the late stages when your character is a tank, swarms of minions that posed a challenge in early stages become just a nuisance, mostly. You are walking legend slaying dragons for breakfast, everybody and their dog knows about your invincibility … but instead of giving you some respect, they try to bite your heels on the first sight. I guess the "fun aspect" of seeing them flee and not restraining your movement at all could be slightly more satisfying than taking them down in a single hit one-by-one for the thousand time.
Other than the meta-answer that the game designers made it that way, or that you may need to farm kills for something in future, there is also the Zerg Rush answer: some creatures are literally bred to swarm their enemies, that's how the hive has always survived before. It doesn't matter how outmatched they are, provided every needling damages you at least a little bit.
There's a similar human need to protect what is precious. Defending your family, defending your motherland. Cities being seiged by a superior opponent don't just abandon the city in cowardice, because they know the opponent will just gain ground and still come after them. They don't want to, they'd rather you stopped, but they have to defend their territories, even if it means their annihilation. If you win, everyone gets killed, ravaged, enslaved, ... If they only have sticks, and you have missiles and jets... they have to use sticks. Can you imagine how they feel?
But yes, you're probably thinking of RPGs where the enemies are preprogrammed with the same hostility no matter what the circumstances, even if you're a God-killer and they're defending 5 coins and half-eaten sandwich in their den.
The original Gothic for example. When you were high level, other low level NPC would rather run.
I also thought hard about the concept, how to make FPS games still fun, but a bit more realistic. The thing is, in most settings this means reducing lots of enemies - as realistic would be, once you start shooting, they all come for you. Not 3. And then maybe another 2. And so on.. and then you would not have a chance, unless you get special powers (or quick save and quick load part of the mechanics)
Similarly, a mindless swarm doesn't present much opportunity for tactics, compared to a group with individual self-preservation instincts, and a manipulatable group morale level, or individual fear level mechanisms. On the other hand it's true that realism is not the goal. Reality is no fun, that's why we're playing a game. But it's a sort of distorted echo of reality, I suppose.
I see somebody in another comment complaining that enemies who get frightened rob the player of the fun of battles. So it depends what it's all about.
> I guess the "fun aspect" of seeing them flee and not restraining your movement at all could be slightly more satisfying than taking them down in a single hit one-by-one for the thousand time.
Chasing enemies is much more annoying than them coming to you, so that would be a punishment to the player.
Players don't like when you punish them in that way, they want to kill the monsters they don't want an upgrade that makes you more powerful make it harder to kill monsters since now they start running.
> Chasing enemies is much more annoying than them coming to you, so that would be a punishment to the player.
It seems I've failed to express myself clearly. The idea was that at some point, "low-level" adversaries simply stand no chance against a "high-level" PC, which should be obvious to both sides -- so acting accordingly on both sides would make sense without taking the fun out of the game, because -- and hear me out -- at that point in the game, chasing the low-level minions should be the last mechanic the player is forced to endure. When you are going for a dragon, you should not be forced to stomp your way past overly self-confident "newts" or mow down swarms of goblin youngsters…
Naturally, if the PC chooses to chase minions fleeing in terror after they took
out the most courageous (or silly) third of their clan, that should be an option… and arguably it could even bring some satisfaction after the PC's low-level struggles, perhaps. But should this be the main mechanic? Definitely not -- at least not in the kind of game my thought experiment addressed.
The truly correct answer is give the player a mild damage aura/aoe and let the mobs die at your feet on their own. Running away breaks an annoying amount of mechanics, like ingredient farming.
The power fantasy just needs them to die trivially. So just do that.
I think games don’t have to be fun. There’s plenty of games where fun would be super inappropriate and yet the games are very popular. This applies to a lot of psychological or survival horror games. I think better is that a game must be compelling. There must be something encouraging you to play more, more so than any frustration or conflict the game introduces.
You definitely don't want too much realism, for most games - you probably don't want to manage bathroom trips! We just assume it happens "off camera"
But when humanoid enemies behave in plainly stupid ways it's a real immersion-breaker for me. I've been gaming a looooong time, so I'm quite adept at the necessary mental gymnastics to enjoy stuff anyway... but... still... games could be better here. (And by "better" I mean "more fun")
"This is, unfortunately, how narcissists behave. It's simply impossible for a narcissist to be wrong. They truly believe themselves to be right, all the time, and will even distort reality around them to "make" it true. And they do it all unconsciously." - kstenerud
You claim "very high quality" but can't even get the basic UI working properly. You wrap tmux and a container in 2k lines of code and claim quality, I think the comment above was aimed at this claim.
I did not much more than a cursory glance too, but found "./sandbox/create.go", a ~1300 lines long file with so much duplication even within just itself that I stopped counting.
Now it was a long time ago I did Go professionally, but I'm also in the camp of "That doesn't really count as high-quality", although I know for a fact you can get quality code out of LLMs, but I don't think that's a good showcase of that.
> I did not much more than a cursory glance too, but found "./sandbox/create.go", a ~1300 lines long file with so much duplication even within just itself that I stopped counting.
Really? What duplication did you actually find? I count a few small ones in buildMounts and ReadPrompt, maybe 20 lines or so, but hardly anything worthy of such an epithet.
Admittedly, the parsing & escaping code and some utility functions could be moved outside to shrink the file, but otherwise I'm having trouble finding issues with the code.
The duplication I'm seeing isn't just "same text repeated" but structural duplication. Doing a quick 5 minute look again just to give you some pointers; runtime.MountSpec construction in buildMounts, Workdir vs aux-dir mount-mode handling, repeated one-off mount append blocks, overlay detection and so on, the list goes on. Just those should account for 200+ lines.
Look for slight variations of the same thing but with different paths, variables, or modes and I think you'd be able to spot the rest as well.
I've noticed that the bar for "quality" when people judge AI is often significantly higher than what they'd hold a human to. I'm not saying GP et al are doing this (I haven't looked myself), but it is a widespread pattern I've noticed both professionally and personally. I don't know why it is.
The bar isn't any higher. There's just no grace given. No one is judging a hobby project made by a human on quality, and the person who the hobby project belongs to will rarely say that their code is high quality. And in a professional setting, I think people are fine with "good enough" but they're not going to claim anything is high-quality.
But people are so quick to label their vibe-coded codebase as high quality and no grace is going to be given to a machine.
What comments are you seeing that are calling code from humans high-quality?
Grace shouldn't be given though. The code from vibe coding should pass the review bar as-is. If you need to iterate, you've defeated the purpose.
Because the end result is people committing bad code. For some random hobby project, sure who cares. But people are using this at work. The codebase is rotting in a new innovative way.
Either the bar has to be set at "actually good code comes out of vibe coding" or you have to accept that codebases are going to steadily become less usable by human coders who use their fingers to type in emacs.
Suddenly every dev needs an agent to even work with the slop. Seems like an outcome Anthropic would love though....
People who use AI set the bar themselves when they claim they generate "very high quality work using Claude". Humans more rarely make such claims about the code they write themselves, but when they do, I expect they face similar scrutiny.
AI code is competent, but it's not great or high quality unless you have a good enough eye for quality to steer it with an iron hand. But if you do, you know the quality comes from proper guidance, so you still wouldn't say AI code is great. If you do say exactly that, it comes across as having low standards (which is fine if you own it) and people are going to jump on that just to bring you down a peg.
> "I've noticed that the bar for 'quality' when people judge AI is often significantly higher than what they'd hold a human to."
Because that is literally the hype being fed to us by the marketers at the AI companies and HN users promoting AI.
- AI promoters: "AI is doing Ph.D level work! LLMs are not just a token predictor, it is actually thinking and reasoning! It will replace all developers, including _you_, so get on board the AI hype train now!"
- AI promoters when confronted with blatant mistakes and reasoning errors from cutting edge models: "Why are you holding LLMs up to higher standards than humans? That's not fair or reasonable."
I have seen it too. The answer is easy - they don’t like AI. I've seen similar things with some people that don’t like women in tech or certain minorities - they suddenly critique at an extremely high level. I also haven’t looked at this particular case, but it wouldn’t surprise me to be the same thing here.
> I also haven’t looked at this particular case, but it wouldn’t surprise me to be the same thing here.
Be surprised then, because me, who left the critique, probably exclusively programmed with agents for the last year or so, so unlikely I think the code is bad because I "don't like AI". I don't love it either, but wouldn't call myself a AI-hater by any measurements, would be weird to write articles like this if so: https://emsh.cat/en/one-human-one-agent-one-browser/
Again, I wasn't reacting specifically to you (as noted, I wouldn't be surprised if so, but I also wouldn't be surprised if not). I was making a more general statement.
Dude, are you for real? We've had the supposed inevitability of AI rammed down our throats since the minute LaMDA convinced Blake Lemoine it was sentient, we've watched CEOs hype up AI as if it were production-ready while it was still barely beta quality, LLM-driven chatbots have been stapled to the side of every product no matter how little sense it makes since OpenAI published an API, and we've been told to prepare for the inevitable "agentic future" even as Claude 3.5 had to have its hand held more than a wet-behind-the-ears freshman summer intern. We're told that this technology is going to eat the entire world economy and render human labor obsolete, starting with our jobs, but if it's genuinely supposed to do that, I think it's more than reasonable to expect it to write superhumanly perfect code, not just code that's incrementally better than the last model release but still bad; extraordinary claims require extraordinary evidence, after all. To liken AI skepticism to the obstacles faced by women and minorities in tech is a category error that trivializes actual human struggles against human prejudices.
https://github.com/kstenerud/yoloai/blob/main/runtime/regist... <- `Register` embeds a copy of the code from `IsAvailable` because of the locking; that could be replaced with a private `isAvailable` that has no locking that both use (after doing their own locking)
Just out of curiosity, I enabled some other linters and it looks bad. Excluding test files, there are 110 functions with a cyclomatic complexity over 10 and 7 that are _over 50_. The worst is at 86, which is mind-boggling.
Could probably find more, but you get the drift. I'm sure it runs, but stylistically this is more along the lines of what I would expect an intern to do.
This is also sort of nit-picky, but like half the stuff in https://github.com/kstenerud/yoloai/blob/main/docs/dev/backe... isn't idiosyncratic, it's just the way those things work and a lot of them aren't even tricky. The one linked is particularly blatant; that's not limited to os.Stat that's literally just how permissions work. Denying permission on inodes is a property of the folder, not the file.
There is no incentive to speak up. Why go against the grain and expend your social capital when you can just do exactly as you're told and not cause any trouble?
There is incentive to stay quiet: getting the paycheck and a stress-free evening with my family.
It’s not discrimination man. People (including bank and post office workers) work during 9-5 working hours, so it makes sense that these services are only open during working hours.
You're right. Why do their customers insist on working the same hours they do? You'd think they'd work different hours so they could run their errands when things are open.
No one presumes you 'should' work 9-5, but that is the way it is, and the bank/postal office/whatever employees don't have the option to work evenings. It is the way it is.
Now whether we could have a better system -- Sure! I'm all for a better society. I'm just saying it's not the way it is because of discrimination or some other conspiracy.
The other commenter mentioned a possible workaround, but you can also authenticate with AWS through env variables. You could store these in sops and have an alias or task that routes your aws commands through sops:
sops exec-env secrets.enc.yaml 'aws something something' # sops injects decrypted credentials into env vars at runtime
Not an interesting story, just wanted to share that the other party might not be aware of how this comes across on the people that have to read their AI messages.
reply