You triggered an old memory of mine in high school of when I ran for class president in senior year and campaign spending was capped at $100 dollars and someone else flagrantly violated campaign finance rules and spent at least a thousand dollars primarily distributing pencils that would go on to litter the campus’ every corner.
Yes. It was a close friend who told me he wasn’t running prior to the nomination deadline. I had done some strong analytics and figured I had great odds. Then I learned, from the dean, that he was running. He split my vote. I learned a lot about life from that experience lol.
The best part about this is that you know the type of people/companies using langchain are likely the type that are not going to patch this in a timely manner.
Langchain is great because it provides you an easy method to filter people out when hiring. Candidates who talk about langchain are, more often than not, low quality candidates.
Would you say the same for Mastra? If so, what would you say indicates a high quality candidate when they are discussing agent harnessing and orchestration?
I'm not familiar with it. My first question would be: Are there any prominent projects that use it?
A lot of these frameworks are lauded, but if they were as good as they claim you would run into them in all sorts of apps. The only agents that i ever end up using are coding agents, i think they're obviously the most popular implementations of agents. Do they use langchain? No, i don't think so. They probably use in house logic cus it's just as easy and gives them more flexibility and less dependencies
I somewhat take issue as a LangChain hater + Mastra lover with 20+ years of coding experience and coding awards to my name (which I don't care about, I only mention it for context).
Langchain is `left-pad` -- a big waste of your time, and Mastra is Next.js -- mostly saving you infrastructure boilerplate if you use it right.
But I think the primary difference is that Python is a very bad language for agent/LLM stuff (e.g. static typesystem, streaming, isomorphic code, strong package management ecosystem is what you want, all of which Python is bad with). And if for some ungodly reason you had to do it in Python, you'd avoid LangChain anyway so you could bolt on strong shim layers to fix Python's shortcomings in a way that won't break when you upgrade packages.
Yes, I know there's LangChain.js. But at that point you might as well use something that isn't a port from Python.
> what would you say indicates a high quality candidate when they are discussing agent harnessing and orchestration?
Anything that shows they understand exactly how data flows through the system (because at some point you're gonna be debugging it). You can even do that with LangChain, but then all you'd be doing is complaining about LangChain.
> And if for some ungodly reason you had to do it in Python
I literally invoke sglang and vllm in Python. You are supposed to (if not using them over-the-network) use the two fastest inference engines there is via Python.
Python being a very bad language for LLM stuff is a hot take I haven’t heard before. Your arguments sound mostly like personal preferences that apply to any problem, not just agentic / LLM.
If we’re going to throw experience around, after 30+ years of coding experience, I really don’t care too much anymore as long as it gets the job done and it doesn’t get in the way.
LangChain is ok, LangGraph et al I try to avoid like the plague as it’s too “framework”-ish and doesn’t compose well with other things.
I used to write web apps in C++, so I totally understand not caring if it gets the job done.
I guess the difference where I draw the line is that LLMs are inherently random I/O so you have to treat them like UI, or the network, where you really have no idea what garbage is gonna come in and you have to be defensive if you're going to build something complex -- otherwise, you as a programmer will not be able to understand or trust it and you will get hit by Murphy's law when you take off your blinders. (if it's simple or a prototype nobody is counting on, obviously none of this matters)
To me insisting that stochastic inputs be handled in a framework that provides strong typing guarantees is not too different from insisting your untrusted sandbox be written in a memory safe language.
What does static type systems provide you with that, say, using structured input / output using pydantic doesn’t?
I just don’t follow your logic of “LLMs are inherently random IO” (ok, I can somehow get behind that, but structured output is a thing) -> “you have to treat them like UI / network” (ok, yes, it’s untrusted) -> static typing solves everything (how exactly?)
This just seems like another “static typing is better than dynamic typing” debate which really doesn’t have a lot to do with LLMs.
he says its bad for agents, nit 'LLM stuff'. python is fine to throw task to the GPU. it is absolutely dreadful at any real programming. so if you want to write an agent that _uses_ LLMs etc like an agent, there are much better languages, for performance, safety and your sanity.
I found the general premise of the tools (in particular LangGraph) to be solid. I was never in the position to use it (not my current area of work), but had I been I may have suggested building some prototypes with it.
I think there are probably lots of thorough critiques, but for me it boiled down to this:
Langchain claimed to be an abstraction on top of LLMs, but in fact, added additional unecessary complexity.
Prompt management was such a buzzword when langchain came out, but 99% of LLM use cases don't need prompt management - GitHub and strings works just fine.
I'll admit that I haven't looked it in a while, but as originally released, it was a textbook example on how to complicate a fundamentally simple and well-understood task (text templates, basically) with lots of useless abstractions that made it all sound more "enterprise". People would write complicated langchains, but then when you looked under the hood all it was doing is some string concatenation, and the result was actually less readable than a simple template with substitutions in it.
yes, in an industry that has rapidly changing features and 7000 of these products that splinter and lose user base so quickly you should write your own orchestration for this stuff. It’s not hard and gives you a very easy path to implementing new features or optimizations.
I went through evaluating a bunch of frameworks. There was Langchain, AG2, Firebase Gen AI / Vertex / whatever Google eventually lands on, Crew AI, Microsoft's stuff etc.
It was so early in the game none of those frame works are ready. What they do under the hood when I looked wasn't a lot. I just wanted some sort of abstraction over the model apis and the ability to use the native api if the abstraction wasn't good enough. I ended up using Spring AI. Its working well for me at the moment. I dipped into the native APIS when I needed a new feature (web search).
Out of all the others Crew AI was my second choice. All of those frameworks seem parasitic. One your on the platform you are locked in. Some were open source but if you wanted to do anything useful you needed an API key and you could see that features were going to be locked behind some sort of payment.
Honestly I think you could get a lot done with one of the CLI's like Claude Code running in a VM.
I am not sure what's the stereotype, but I tried using langchain and realised most of the functionality actually adds more code to use than simply writing my own direct API LLM calls.
Overall I felt like it solves a problem doesn't exist, and I've been happily sending direct API calls for years to LLMs without issues.
JSON Structured Output from OpenAI was released a year after the first LangChain release.
I think structured output with schema validation mostly replaces the need for complex prompt frameworks. I do look at the LC source from time to time because they do have good prompts backed into the framework.
IME you could get reliable JSON or other easily-parsable output formats out of OpenAI's going back at least to GPT3.5 or 4 in early 2023. I think that was a bit after LangChain's release but I don't recall hitting problems that I needed to add a layer around in order to do "agent"-y things ("dispatch this to this specialized other prompt-plus-chatgpt-api-call, get back structured data, dispatch it to a different specialized prompt-plus-chatgpt-api-call") before it was a buzzword.
It's still not true for any complicated extraction. I don't think I've ever shipped a successful solution to anything serious that relied on freeform schema say-and-pray with retries.
> so it's not a panacea you can count on in production.
OpenAI and Gemini models can handle ridiculously complicated and convoluted schemas, if I needed complicated JSON output I wouldn’t use anything that didn’t guarantee it.
I have pushed Gemini 2.5 Pro further than I thought possible when it comes to ridiculously over complicated (by necessity) structured output.
When my company organized an LLM hackathon last year, they pushed for LangChain.. but then instead of building on top of it I ended up creating a more lightweight abstraction for our use-cases.
No dig at you, but I take the average langchain user as one who is either a) using it because their C-suite heard about at some AI conference and had it foisted upon them or b) does not care about software quality in general.
I've talked to many people who regret building on top of it but they're in too deep.
I think you may come to the same conclusions over time.
I built an internal CI chat bot with it like 6 months ago when I was learning. It’s deployed and doing what everyone needs it to do.
Claude Code can do most of what it does without needing anything special. I think that’s the future but I hate the vendor lock in Anthropic is pushing with CC.
All my python tools could be skills, and some folks are doing that now but I don’t need to chase after every shiny thing — otherwise I’d never stop rewriting the damn thing.
Especially since there’s no standardizing yet on plugins/skills/commands/hooks yet.
> I hate the vendor lock in Anthropic is pushing with CC.
Accepting any kind of vendor lock in within this space at the moment is an incredibly bad idea. Who knows what will get released next week, let alone the next year. Anthropic might be dead in the water in six months. It's unlikely but not impossible. Expand that to a couple of years and it's not even that unlikely.
This question doesn’t have anything to do with skills per se, this is just about how different agents handle context. I think right now the main way they cull context is by culling noisy tool call output. Skills are basically saved prompts and shouldn’t be that long, so they would probably not be near the top of the list of things to cull.
Claude Code subagents keep their context windows separate from the main agent, sending back only the most relevant context based on the main agent's request.
Is there any tool that allows you to pass the line numbers that you want to stage as arguments to the command, instead of having to do it interactively?
Mercury's customer data breach was soooo damaging.
For those unaware, there was a breach at mercury that gave attackers the following information (from their site):
- Business and Beneficial Owner Information:
- Name(s)
- Phone numbers
- Addresses
- Email addresses
- Account Details:
- Overall account balance
- Business bank account numbers
- Business EIN
- Transaction Information:
- Entities you transact with
- Sender and receiver’s address
- Account number
- Transaction amounts
Despite all that, a web search does not reveal a post-mortem by Mercury. I don't know why you'd trust them.
That’s hilarious. I had cursory familiarity with the McDonald’s situation but did not know thread agency aspect. I’d be very curious how many “hours” were spent minus the inference time.
I've been a long time HN reader but never created account since I never posted. I built the site to solve my own problems and just thought it was cool to share it with the community that I enjoyed :D
I think people are setting themselves up for failure if they index their happiness or sense of self satisfaction to their ability to discern what AI-generated content is or not.
Soon, we’ll have no idea what’s AI-generated or not. I care about good, tight story telling.
Part of watching films and animations was that seeing that a human created this inspired the wish to create in yourself. When all they did was enter a prompt that takes some of the magic away.
If all you care about is just the story then maybe you personally will be satisfied but a lot of people cared about the animations, cinematography, etc, and all of the work that went into that.
I think digital effects still rarely look as good as the peak of Hollywood practical effects (call it… idk, Alien in 1979 through Independence Day in ‘96 or so, roughly, and yes I know ID4 also had computer fx in addition to lots of miniatures and models)
Having to do things for-real also kept things grounded. Modern action movies are often cartoon-like with supposedly human characters stringing together super-human moves that’d leave a real person with dislocated shoulders, broken bones, and brain damage, because they’re actually just CG, no human involved.
[EDIT] OMG, or take Bullitt (1968) versus, say, the later Fast and the Furious sequels (everything past Tokyo Drift). The latter are basically Pixar's Cars with more-realistic textures. They're cartoons with live-action talking segments. Very little actual driving is depicted. Bullitt may have used the movie-magic of editing, but someone did have to actually drive a car, for every shot of a car driving. Or at least they had to set up a car with a dummy to convincingly crash. What you're seeing is heightened, but basically within the realm of reality.
Or take A Bridge Too Far. It's a bit of a mess! Make it CG and it'd be outright bad. But ho-lee-shit do they blow up a lot of stuff, like, you cannot even believe how much. And look at all those tanks and armored vehicles they got! And planes! And extras! Those are all 100% real! AND ALL THE KABOOMS! And it all looks better than CG, to boot. The spectacle of it (plus some solid performances) saves the movie. Make all the FX CG and it'd be crap.
Imagine a Jackie Chan movie with CG stunts. What is even the point. It'd be trash.
This was the argument about Fury Road (mostly real) vs Furiosa (a lot of CGI.)
But only bad CGI is visible. I guarantee you have watched CGI footage and not noticed. At all.
The problem over the last decade or so hasn't been the technical limits of CGI, but studio unwillingness to spend enough on it to make it good.
And directors have also become less creative. You can find UK newsreels from the 50s on YouTube, and some of the direction and editing are superb - a beautiful mix of abstraction, framing, and narrative.
Most modern directors don't have that kind of visual literacy. The emphasis is more on spectacle and trying to bludgeon audiences into submission, not on tastefulness and visual craft.
This was the argument about Fury Road (mostly real)
Fury Road is pure wall to wall CGI. People keep pointing to it as some example of doing things with live action when the entire movie is soaked with CG and compositing.
It's a lot of CGI, but done in realistic ways. A lot of the examples from the article (which is a very good article, thank you for linking it) were mostly about paint-outs, color grading, or background elements.
There's a good chunk of modern blockbusters that will CGI everything in a scene except the lead actor's face - and sometimes that too.
Predates computers, they used to paint out wires and whatnot by hand and it usually looked just as good.
> Compositing
Predates computers. They've been doing it since forever with miniature overlays, matte paintings, chromakey, double exposures, and cutting up film negatives with exacto blades.
> color grading
Literal cancer which ruins movies every goddamn time. The fact that they shoot movies with this kind of manipulation in mind changes how they use lighting and makes everything flat with no shadows, no depth, everything now gets shot like a soap opera. This also applies to heavy use of compositing too. To make it cheaper to abuse compositing, mostly so the producers can "design by committee" the movie after all the filming is done, they've destroyed how they light and shoot scenes. Everything is close up on actors, blurred backgrounds, flat lighting, fast cuts to hide the lazy work. Cancer.
I'm talking about Fury Road too BTW. It's crap. Watch the original Mad Max, not Road Warrior, then watch Fury Road. The first is a real movie with heart and soul, the world it depicts feels real. The latter feels like a video game, except it somehow comes out looking even less inspired and creative than the actual mad max video game that came out at the same time.
But yeah, they made some real weird cars for the movie. That's fine I guess. The first movie didn't need weird cars, it had this thing called characters. Characters who felt like real people, not freaks from a comic book.
Exactly - they've been doing paint outs and composite shots forever! It doesn't feel fundamentally different to do it "on a computer," to me. They aren't using it to show off, just to make the scene look how you'd expect it to.
They've also been doing color grading forever - digital just makes it way cheaper and easier. Before, you'd have to do photochemical tricks to the film, and you would use different film for different vibes.
I'd argue that the ease of digital manipulation has led some studios to do what you say - postpone creativity until after the movie is mostly shot, which leads to that design-by-committee feeling. That sense of 'don't worry, we'll fix the lighting it the editing room' is the same sloppiness as 'and then the big gorilla will use his magic attack and it will look really cool,' without any thought given to it's actually going to look like. But that's not really a failure of CGI itself - that's a failure of vision, right? If you procrastinate making artistic decisioms for long enough, there's not actually going to be any art in the movie once it's done.
I have watched the original Mad Max, and it was pretty alright. If I had watched it at the right age, I probably would have imprinted on it.
It used to be the case that movies had to be made carefully, with the intended look in mind when they were shooting it. Compositing, etc aren't new, as we both know, but the way they're used has changed; they're used far more than ever before, with important design decisions about the look of the movie deferred to the very last minute ans everything up to that point done in such a way to facilitate making late last minute changes. This is absolute poison for cinematography as an art. Very few big budget movies made in recent years has any artistic merit for this reason. Producers now feel like they have the technology to make all the decisions that, by technical and logistic necessity, the directors/cinematographers would have to make themselves years ago. And the producers are just assholes with money, they cannot make art.
With respect to Mad Max, I think it aged like a fine wine. I didn't first see it when I was young, I saw Road Warrior first. But Road Warrior and everything after it is very camp. Mad Max is more grounded and feels like a commentary on our times, not pure fantasy spectacle. I think the best time to watch Mad Max was the 70s, and the second best time is probably today. In the 90s or 00s it wouldn't have hit right.
I'd argue that the ease of digital manipulation has led some studios to do what you say - postpone creativity until after the movie is mostly shot,
None of this is true. You can't shoot plates and do whatever you want later. Even basic effects shots take intricate planning. They were talking about cleaning up mistakes and small details.
which leads to that design-by-committee feeling
I'm not sure what this means in the context of a movie but it isn't how movies are made.
There are art directors, production designers and vfx supervisors and they answer to the director. Movies are the opposite of design by committee. It isn't a bunch of people compromising, it is the director making decisions and approving every step.
that sense of 'don't worry, we'll fix the lighting it the editing room'
This doesn't happen because it isn't how anything works. You can fix lighting in editing.
the same sloppiness as 'and then the big gorilla will use his magic attack and it will look really cool,' without any thought given to it's actually going to look like.
Enormous thought and planning is given to every stage. This idea of not liking lots of effects in fantasy or comic book movies and then attributing that to sloppiness or apathy simply does not happen in big budget movies. There are multiple stages of gathering reference, art direction and early tests, many times before any photography is shot.
If you procrastinate making artistic decisioms for long enough, there's not actually going to be any art in the movie once it's done.
Not only does this not happen, it doesn't make sense. Just because you don't like something that doesn't mean huge amounts of work and planning didn't go into it.
The person I replied to said it was "mostly real". Lots of CG is done in realistic ways but people pick and choose what they decide is good based on the movies they already like. Fury Road has somehow become an example of "doing things for real" when the whole movie is non stop CG shots.
A lot of the examples from the article (which is a very good article, thank you for linking it) were mostly about paint-outs, color grading, or background elements.
No they weren't, there are CG landscapes, CG mountains, CG canyons, CG crowds, CG storms, CG cars, CG arm replacements and many entirely CG shots. It's the whole movie.
Are you suggesting it's not noticeable in those movies? I found it distracting several times in I think every one of those (maybe the least in 1917? And I haven't seen Ford vs. Ferrari, but I have all the rest). A few entire scenes or sequences in TG:M look awful, and it's usually the mundane ones that wouldn't even have been effects in a pre-CG movie, not the aircraft action stuff. Alien: Romulus looks fake practically the whole movie (that one didn't ruin it for me or anything, but it had an effect like the Riddick movies, of being obviously mostly a cartoon, though of course not as awful about it as those were).
Well, I guess it wasn't exactly distracting in Barbie because that's practically a marionette movie a la Thunderbirds, so it's not really trying not to look off.
> Are you suggesting it's not noticeable in those movies
You can check the youtube link I posted. You'd be hard pressed to notice the good CGI in those movies.
> I found it distracting several times in I think every one of those
Honestly, I really doubt you noticed that much CGI. Well, unless you go in already primed to discount everything as CGI (whether or not it's actually CGI).
Current-era CGI is insanely good. The problem is that it's used and abused everywhere, often with very little consideration for whether it's needed, or if there's time to do all the VFX shots etc.
I think eliminating the need to think and work around reality is part of the trouble. Not that it ruins everything (people take HN posts as so maximalist even when they factually are not; see: the rest of this comment tree) but I think the lack of the odd limitation or need to think about how to solve a problem without resorting to “render it in a computer” causes significant harm to cinema overall. I’m not (see above parenthetical) claiming it’s net-negative, but there’s a kind of film-making skill and genius that was once on display pretty widely, and now is not.
I mean for fuck’s sake, they’d probably CG the paint buckets in Home Alone if they made it today. And we’d get some tasteless can-cam shot, because you don’t have to figure it out, you can just do it. And they’d look fake because they’d move too perfectly, lacking the kinds of little off-seeming movements that a real paint can in a real take might do. Never might the can obscure a few frames of face when the directors might choose otherwise, and the result will be obviously CG through its convenience if not due to outright flaws.
Excessive perfection and too many things moving the optimal way for the shot or exactly the way the viewer expects are under-appreciated tells of CG, and they’re deadly ones, present even in a lot of “perfect” CG (give it a few years, we thought the CG in Lord of the Rings was convincing and now it looks like trash). They need to start CGing their fake environments sometimes doing something slightly less than ideal to an actor’s jacket, or something, and not to call attention to it as a comedy relief moment, but because “that’s just what happened” (not really, but it’d make the effects more convincing)
> CG through its convenience if not due to outright flaws.
It's also over-reliance on this convenience. Bad shot? We'll fix it in post. Objects missing, or in wrong places, or too many of them? We'll fix it in post. Bad sound, camera position, actor unavailable? Believe it or not, post.
And many don't even think whether you should prepare the shot for post-production, or even give vfx teams more time to complete the work
This is just rose tinted nostalgia. You are remembering the things you loved which are much simpler and forgetting all the lemon shots and limitations of the day.
The movies and TV that can be made now without the limitations of the past are significantly different, from period movies to super hero movies and everything in between. Watch the 1970s superman or logan's run and see how they hold up.
The vast majority of CG is replicating stuff like set design or replacing a location shoot. We don’t usually call that an “effect” when it’s not done with a computer. And even then… it continues to deliver “bad matte painting” often enough that spotting such failures in the wild isn’t hard (nor was it hard with bad matte paintings!)
[edit] my point, anyway, isn’t that any given effect is better. It’s not even necessarily that the movies are better (The Passion of Joan of Arc barely had effects at all, and didn’t have synced sound, for god’s sake, an it’s incredible—of course CG-having movies can be great) but that I tend to find the overall effect of those movies better. Those “seamless” mundane CG effects shots of things like composited computer-generated rooms or streets rarely get the kind of attention a real set does, and the movies suffer for it. Nobody had to move around the space with their real body and think about it, and it usually (usually! Not every single time) shows, if not in anything wrong, exactly, then in the degree to which it’s perfectly forgettable and fails to contribute anything but filling screen space.
[edit edit] more to the point, peak practical wins at convincing effects in the Big Damn Action Moment. But only peak, and that was a tragically brief span. Point me to a CG sci-fantasy space fight that looks better and/or more like a real thing that’s happening than the battle above Endor in return of the Jedi (you’ll notice I didn’t pick the earlier two movies, as Jedi is where they really perfected it all—though even the first has some shots that are quite convincing!). Like truly if you know of one I’d love to see it. I never have. They all look plainly computer generated. I’m not saying every frame of those SFX shots in Jedi is perfect, but it looks overall more real than anything similar I’ve seen done in a computer. Like you’d think in about 40 years it’d have been surpassed multiple times, but no. They all look CG.
Or, like… put the best 50% of practical shots in Jurassic Park against the best 50% of CG-heavy dino action shots in any Jurassic Park from 3 on. They’re more convincing than any of the CG shots. (Some, from the field of all practical effects shots in the film, are not convincing! But a hell of a lot are, and not just better than the median CG effect in later JPs or something, but better than all). We struggle to touch the tippy-top peak of that craft with computer effects, still today.
The vast majority of CG is replicating stuff like set design or replacing a location shoot.
Says who?
We don’t usually call that an “effect”
Who is "we" ?
This is basically going from "CG is bad" to "not all CG" to "that's not an 'effect'". These arguments never hold up because any explanation ends up full of holes and inconsistencies.
Usually it just ends up being a variation of "I liked the movies I saw when I was a kid". Most of what you're saying here is just that you liked an old movie.
People have been making the argument of 'models look more real' since the 90s, but when it comes down to it, they don't know what is CG and what isn't and can't tell the difference. It's a combination of nostalgia and thinking they know better when they aren't actually being tested.
Then there is the fact that shots in modern movies can't be made without CG. You can't do the same things with models and have the camera freedom, long shots, wide shots etc, and that's just hard surfaces.
Saying "I love this black and white movie, therefore CG is over used" is an opinion that most people would never hold and a connection that doesn't make a lot of sense, but the a cold hard fact is that the same movies can't be made. Eventually seeing a half second jump scare of an alien is going to get old even if the man in the suit looks good.
> > The vast majority of CG is replicating stuff like set design or replacing a location shoot.
> Says who?
The people who are like "actually there's a ton of CG you don't notice!". They mean simple compositing, CG backdrops, painting in props, and stuff like that. (as if I'm not already aware of that stuff, LOL) That's where most of the CG is in movies for the last decade or so—they're right about that. It's replacing prop construction, set design & construction, and location shooting.
> This is basically going from "CG is bad" to "not all CG" to "that's not an 'effect'". These arguments never hold up because any explanation ends up full of holes and inconsistencies.
No, I'm just not impressed when CG successfully (I disagree it's successful as often as proponents say, and to them I say "give it ten years and a lot of this 'good' stuff will look awful to you", as it's the same ride we've been on with CG the entire time so far, the "look, CG's finally entirely convincing!" movie seems about as convincing as Jason and the Argonauts' stop motion a few years later) does something mundane that wouldn't even have been an effect before.
I mean, if we're counting that, and trying to compare the two, then just about every single time a location shoot was used where CG might have been today, classic "effects" win. That part's silly to compare.
> People have been making the argument of 'models look more real' since the 90s, but when it comes down to it, they don't know what is CG and what isn't and can't tell the difference. It's a combination of nostalgia and thinking they know better when they aren't actually being tested.
The best of the best just really do hold up better. It's a shame we didn't get more time with that style before CG took over, it was a pretty brief window between "you can always tell the model is a model" and "now it's all computers".
(This should irk you too: CG blood spatter harms every single action movie where it replaces squibs, the movie may survive the harm but that part is terrible every time)
The people who are like "actually there's a ton of CG you don't notice!". They mean simple compositing, CG backdrops, painting in props,
No, it's everything. Modern big budget movies could have 800-1200 vfx shots. You aren't able to guess at what is photography in every shot in a few seconds 800 times during a movie. You can make that claim, but even people who have been doing vfx for decades can't do it. People say these things because they want to believe it and they know they won't be tested to prove it.
I mean, if we're counting that, and trying to compare the two, then just about every single time a location shoot was used where CG might have been today, classic "effects" win. That part's silly to compare.
The best of the best just really do hold up better. It's a shame we didn't get more time with that style before CG took over
You say this but again, you don't know how every shot was done and every shot is different. This mostly comes from people wanting to think they are never 'fooled' and 'old ways are better'. This has been going on and repeated since the 90s.
The truth is that you aren't in a position to judge what is 'best' because you don't know how every shot was done in the first place.
I think this might be your nostalgia. The thing looks different in different scenes, and there's a scene that feels like it's a guy inside from the way it moves. So I disagree that Alien is peak special effects. (still peak over things. Peak ambience for sure)
I didn't pick perfect examples, I picked useful ones for bounding the rough time period. Both examples are transitional.
Alien nails it like 80% of the time (I've watched it twice in the last year, in 4k on a wall-size screen, so it's fresh for me). It's an early, major example of getting it damn near perfect pretty often. Not every shot's great—like, about two-thirds of the shots of the exterior of the landing craft look like a miniature, not as glaring as a Showa-era Godzilla or anything, but you can tell—but it's still a better average than modern computer-heavy movies. It's one of the earliest that's exhibiting the potential of peak pre-CG special effects, if not nailing it all the time. But, very few movies nail it all the time, including modern ones doing the computer graphics thing.
There’s an argument to be made that by watching higher image quality versions, you’re losing on the experience. I.e. the blurriness helped the effect. Their nostalgia and your (presumably) more recent viewing are then two different watching experiences.
That's very romantic. The golden age of both cinema and animation was an assembly line, often an exploitative one. Most frames were the by product of industrial labor, done by people with little autonomy, low wages, no creative input... the human element was already highly concentrated among a very small elite, and, the majority of the labor pool was treated as mechanical/replaceable input. "seeing that a human created this inspired the wish to create in yourself." Sure, but, it's not reeeaaally “a human did it.” It is more “a small number of visible artists did it.”
But nevertheless, a human did still do it. How gruelling and exploitative the process was, or how many humans it took, is beside the point. The fact that the image existed meant that there was an attainable skill that a person could learn in order to do that same thing, and that was inspiring.
Since the days of cave paintings, that experience has been available to all humans. In the year 2025, it died, and I will never experience it again.
I get it, but it also doesn't matter. I liked anime when it was drawn by hand because I liked looking at all the things people could draw. But it doesn't matter what I like; virtually all anime is now rendered from 3d computer models, particularly any sort of machinery or whenever the camera rotates or transforms in space showing off the 3d structure of things. That stuff used to be drawn by hand but now nobody does that. It's not coming back.
Good film making is good film making. I am a creative. I incorporate AI into videos that I make subtly and with a huge amount of care. I know I put more time and care into my craft than most others.
Nobody knows what involved AI and what didn’t. At the end of the day, if you care about your work, it shows.
I can almost see your point, but there are two big problems:
1) To date, there has been no example of AI that is good. It's not even close.
And 2) Why should I be interested in a story nobody was interested in telling? If you don't want to make a video, or tell a story, or write a song, then...just don't. Why even have an AI do it?
It's wild that you would make this claim without taking a few seconds to drop a link. It's such a substantial, controversial claim, it really needs some kind of evidence.
What does a visualization being to the table over a book, if it's executed in the most generic way possible? The decisions made when adapting one medium to another are what does or doesn't make it worthwhile.
Unless your goal is purely to capture people who don't and won't read, as cheaply and cynically as possible.
there is a big difference between sending the story to the AI and saying "visualize this" vs carefully describing exactly how the visualization should look like and effectively only using the AI to render your vision.
well the question is rather, what is the difference of AI use vs say a 3D modelling application?
assuming you have the 3D assets already designed. you then take a model, and instruct the application that this model is to move from point A to point B, using a pathfinding algorithm while avoiding obstacles. once done, render the result in a video.
now do the same with AI. is the human contribution really that much different?
I think the objections with AI will change based on the quality of the AI generated work. What people don't want is to wade through a million gallons of poorly generated slop to see one good movie. They also don't want to have to deal with thousands of zero effort AI videos just to find one good video generated by a human being.
If the actual result of AI is an unlimited supply of adequate media personalized to our tastes, I don't foresee there being any objection. Right now, it's honestly just shovelware on a scale that hasn't been seen before. No one likes shovelware except maybe toddlers.
If we ever get to that point...im still ambivalent. I also get exposed to media to form community. And Ai very explicly wants to tear down communities and create a factory of slop. Even if we can get some good Ai storytelling, I'm not sure if a tree fighting the flood is enough. It's going to topple eventually as the roots get washed out
>In the case of this ad.. it’s okay?
I thought it was cute. I can nitpick, but it gave a feeling of family and community, and how you can't form that by devouring your peers.
The McDonald's ad meanwhile : "the world's going to shit, use McDonald's as your apocalypse bunker! (no loitering tho)". Heck, it feels like the kind of ad Fallout or Outer Worlds would make on an in-game TV.
Also, usage and billing takes a DAY to update. On top of that, there are no billing caps or credit-based billing. They put the entire burden on users not to ensure that they don't have a mega bill.
reply