I think that the problem is, at the end of the day, the engineer must specify exactly what they want the program to do.
You can do this in Python, or you can do this in English. But at the end of the day the engineer must input the same information to get the same behavior. Maybe LLMs make this a bit more efficient but even in English it is extremely hard to give exact specification without ambiguity (maybe even harder than Python in some cases).
Also Christianity was a Levantine religion, growing fast in Greece, Asia Minor, Egypt, Syria, and the Levant. The Eastern Roman Empire at the time was far richer, more urbanized, closer to the grain supply, and closer to Silk Road and Black Sea trade access.
Based on some of his other actions (like moving the capital), I'd speculate Constantine's conversion was part of a deliberate pivot to focus on the East (which paid off, as the centralized Byzantine state went on to survive much longer than its Western counterpart). I'm speculating because inferring his intentions has no historical evidence afaik.
I think there are more possible answers? Jason's mother differs depending on the author...
For example, Jason's mother was Philonis, daughter of Mestra, daughter of Daedalion, son of Hesporos. So Jason's maternal great-grandfather was Hesporos.
Am I the only one who thinks that R1 is awful at creative writing? I've seen a lot of very credulous posts on twitter that are super excited about excerpts written by DeepSeek that I think are absolutely absymal. Am I alone in this? Maybe people have very different tastes than I do?
(I have no formal training in creative writing, though I do read a lot of literature. Not claiming my tastes are superior - genuinely curious if other people disagree).
It's full of inconsistencies, written by someone imagining the sea who has never seen the sea. For example, salt crusted wings of a gull. Gulls don't have salt crusted wings.
It tends towards purple prose and doesn't maintain internal consistency in its own world. He sleeps on a pallet but swings his feet off the edge.
This looks like my experiments to get R1 to write fiction and I think it’s worse than what you get from openai. For instance, it’s using very colorful language to describe a place that’s both a remote fishing village on the edge of a cliff hours before dawn, and a bustling wharf with chattering laborers and large ships anchored in the distance. It also starts by saying the protagonist wakes up with his mouth tasting like blood, that he was screaming, and that his throat is hoarse from holding back from screaming. It’s very colorful but it’s very confusing to read.
I suspect you can update the prompt to make the setting more consistent, but it will still throw in a lot of inappropriate detail. I’m only nitpicking because my initial reaction was that it’s very vivid but feels difficult to understand and I wanted to explain why.
I agree that it felt hard to read. It also doesn't make sense that they're fishing in a storm. But from a prose perspective I don't think it's cringe, which is an improvement from my expectation. I'd share some of the writings I think are terrible but I don't like to pick on people.
If R1 one-shotted this then I revise my opinion somewhat. This doesn't give me a gut "this is awful" emotional reaction (although I don't think it's good - it's pretty cliche, and I found my eyes glossing over pretty quickly).
I was somewhat turned off of DeepSeek (the first few questions I gave it, it returned 100% hallucinated answers). But maybe I'll have to look into it more, thanks.
I regenerated a page a few times but yeah, I gave no other instructions besides that. Also I approached things page by page. That was 3 pages.
It's cliche but this was the prompt:
I want you to write the first book of a fantasy series. The novel will be over 450 pages long with 30 chapters. Each chapter should have between 15 to 18 pages.
Write the first page of the first chapter of this novel. Do not introduce the elements of the synopsis or worldbuilding and story details too quickly. Weave in the world, characters, and plot naturally. Pace it out properly. That means that several elements of the story may not come into light for several chapters.
I had a lot of success with it coming up with decidedly not cliche world building elements after I arranged a sort of interview style interrogation (It asked me questions about what I was looking for generally and generated world building elements along the way).
However, once you start giving a lot of information about the world etc in the prompt as well then the pacing gets weird.
I'm looking for a new job, so I've been grinding leetcode (oof). I'm an experienced engineer and have worked at multiple FAANGs, so I'm pretty good at leetcode.
Today I solved a leetcode problem 95% of the way to completion, but there was a subtle bug (maybe 10% of the test cases failing). I decided to see if Claude could help debug the code.
I put the problem and the code into Claude and asked it to debug. Over the course of the conversation, Claude managed to provide 5 or 6 totally plausible but also completely wrong "fixes". Luckily, I am experienced enough at leetcode, and leetcode problems are simple enough, that I could easily tell that Claude was mistaken. Note that I am also very experienced with prompt engineering, as I ran a startup that used prompt engineering very heavily. Maybe it's a skill issue (my company did fail, hence why I need a job), but somehow I doubt it.
Eventually, I found the bug on my own, without Claude's help. But leetcode are super simple, with known answers, and probably mostly in the training set! I can't imagine writing a big system and using an LLM heavily.
Similarly, the other day I was trying to learn about e-graphs (the data structure). I went to Claude for help. I noticed that the more I used Claude, the more confused I became. I found other sources, and as it turns out, Claude was subtly wrong about e-graphs, an uncommon but reasonably well-researched data structure! Once again, it's lucky I was able to recognize that something was up. If the problem wasn't limited in scope, I'd have been totally lost!
I use LLMs to help me code. I'm pro new technology. But when I see people bragging on Twitter about their fully automated coding solutions, or coding complex systems, or using LLMs for medical records or law or military or other highly critical domains, I seriously question their wisdom and experience.
Agree. Also, Kubrick's other works strongly emphasize lighting, composition, music, and effects over plot. Just look at Barry Lyndon's candlelit scenes (which look like paintings by the Dutch masters), Eye's Wide Shut's Christmas lights, Clockwork Orange's use of Beethoven, or 2001's match cut from a bone to a spaceship. You can't achieve those in a book, because they are purely audiovisual phenomena. And movies have different constraints: like time limits.
King doesn't have to worry at all about what the score is, or how to film a wall of blood. It's simply not part of the medium. The requirements and constraints are completely different.
Aaaand... there's actually a much more relevant set of quotes about The Shining, like:
There's a lot to like about it. But it's a great big beautiful Cadillac with no motor inside. You can sit in it, you can enjoy the smell of the leather upholstery -- the only thing you can't do is drive it anywhere. So I would do everything different. The real problem is that Kubrick set out to make a horror picture with no apparent understanding of the genre. Everything about it screams that from the beginning to the end, from plot decisions to that final scene -- which has been used before on "The Twilight Zone."
My hypothesis:
Lack of geographically local experts.
We've merged more and more into a megasociety. In a geographically distributed society, the power law for quality is more forgiving. You can be the best local band and make a living.
Now that we have ultra-efficient communications, there's less room for "mid-tier" art. Local art gets outcompeted by whatever the top stuff is among a much greater national or international population.
Because of this, there's also less of a breeding ground for maturing artists, or for experimental styles in isolated areas (think California surf rock, or NYC Salsa, etc). There's no place to go if you're not the best.
In one way that's true: An artist has to appeal to a global audience. A global audience does have a taste for local weirdness, but there's a lot less economic basis for locally weird things to spawn and germinate when every video goes online instantly. On the other hand, local weird shit blows up all the time on the internet into cross-cultural global phenomena. So it's not that it stopped existing, just that the economic model has changed.
Definitely an important factor. Industrial scale can wipe out diversity and with it subtlety, which in cultural terms means impoverishing artistic vocabulary and range.
My dim view is that it's just a rapacious monopolistic society. Why are there only three (four-ish) cell phone carriers in the US? Why are there only two app stores? Three (four-ish) major music platforms? The internet should have brought a diversity of choice that has failed to materialize because enforcement of monopoly laws in this space has been nascent and aggressively fought against.
> Local art gets outcompeted by whatever the top stuff is among a much greater national or international population.
It's the lack of access to infrastructure. Look at ticketmaster. You have to be this giant internationally recognized act to be able to afford the grift they're going to apply against you and your fans. The mid teir acts just can't access this space without financially or legally ruining themselves.
It's similar to the labor market. Monopolies _do_ make for more efficient consumer experiences. They completely _destroy_ the labor market to do this. Gains don't come from nowhere. It's no different for communications. Why are there only 6 major consumer ISPs? And look at who we let own some of them.
> there's also less of a breeding ground for maturing artists
I don't think that's true. There are cities where the venue spaces have been bought out and there are few places where these artists could draw a paying audience. It's not true everywhere though, and in those places, local artistry still thrives, but they run into the next problem...
> There's no place to go if you're not the best.
I think back to the 70s to 90s period of music. It was _incredibly rare_ that a new artist had a "good first album." It was usually barely tolerable, but you could see the kernel of something, something worth _investing_ in. Bruce Springsteen famously didn't make "good music" until his third album. Like anything else it takes time, experience, a little assistance, and long tours all across everywhere to build up the fan base.
Once the pipeline of Talent Agencies -> Production Companies -> Studio Companies -> Venue Ticketing got built you didn't need to do any of that anymore. You could literally grab 5 guys from a mall and _force_ them to be a hit in a few months. Being "the best" simply wasn't a factor anymore, they monopolized everything, why would they bother? Managing "the best" artists is a legal and marketing nightmare. Scumming up pretty girls and boys from malls and locking them down in embarrassing contracts is so much easier.
Anyways there are viable talent pipelines that still exist, but they need real investors, which they can only get if we break up the monopolies that prevent them from functioning somewhat properly, as they used to.
> enforcement of monopoly laws in this space has been nascent and aggressively fought against.
Monopoly laws in every space, since the ‘70s. Chicago School judges in the mid and late ‘70s changed the criteria for the government to pursue antitrust enforcement, so now it’s damn near impossible. The results were predictable.
> My dim view is that it's just a rapacious monopolistic society. Why are there only three (four-ish) cell phone carriers in the US? Why are there only two app stores? Three (four-ish) major music platforms? The internet should have brought a diversity of choice that has failed to materialize because enforcement of monopoly laws in this space has been nascent and aggressively fought against.
I think some of this aggregation is due to economies of scale, though.
> You could literally grab 5 guys from the mall and __force__ them to be a hit in a few months.
This is sort of a corollary to my hypothesis. Since we have a megasociety, everyone has access to music from everywhere, but limited time. There’s too much music being produced. So we now have a signaling game (advertising and marketing) to determine who people listen to. Signaling games will naturally be dominated by capital.
In terms of breeding grounds for local music, where are you thinking? Nashville?
You've ignored the fact that discovery is now a new service component that really didn't exist before. We can tag music and artists and we can automatically discover related music and artists very easily. All the major services do this. Think of an expanded and federated (all the way back to the artist) open source version of this.
There's no reason to think that the previous model somehow produced the most efficient way of "determining who people listen to." It was almost certainly suboptimal. It's no surprise then that this suboptimal model was more or less copied onto the internet and all new players bought out so no new model could be revealed.
The lack of available artistry and market for it extends through multiple levels, and in this case, right into the software stack that _should_ exist for artists to self publish and for listeners to automatically discover.
> You've ignored the fact that discovery is now a new service component that really didn't exist before. We can tag music and artists and we can automatically discover related music and artists very easily. All the major services do this. Think of an expanded and federated (all the way back to the artist) open source version of this.
This is a good point. We have gone from diffusion-constrained to search-constrained. No clue what to make of that. I would submit to you that the amount of time people have to consume art has not changed, and that improved search now pushes people to consume the globally best art rather than niche content. Are there any domains or platforms that you think do a good job of surfacing specific niche content? Or am I misunderstanding your point?
>There's no reason to think that the previous model somehow produced the most efficient way of "determining who people listen to." It was almost certainly suboptimal. It's no surprise then that this suboptimal model was more or less copied onto the internet and all new players bought out so no new model could be revealed.
It's not about efficiency. I think the current system is more efficient (hence economies of scale). It's just that the rent extraction/profits are concentrated among the platform owners rather than spread out among local venue owners and artists.
> The lack of available artistry and market for it extends through multiple levels, and in this case, right into the software stack that _should_ exist for artists to self publish and for listeners to automatically discover.
I agree it should be possible, the problem is setting up the incentives correctly.
> It's not about efficiency. I think the current system is more efficient (hence economies of scale). It's just that the rent extraction/profits are concentrated among the platform owners rather than spread out among local venue owners and artists.
Chiming in again. In some ways, this is "efficiency". Serving the globally best stuff is more efficient. The problem is we are trading exploration/variety for exploitation/efficiency. Reasonable minds may differ as to how that should be handled.
You can do this in Python, or you can do this in English. But at the end of the day the engineer must input the same information to get the same behavior. Maybe LLMs make this a bit more efficient but even in English it is extremely hard to give exact specification without ambiguity (maybe even harder than Python in some cases).