Don’t forget EXAPUNKS by the same dev! They really perfected the formula in that one.

That sounds like Flanderization to me https://en.wikipedia.org/wiki/Flanderization

From my experience with LLMs that's a great observation.

I also never see this behaviour, but I pretty much only use the tube for commuting at peak times. I think commuters are generally better behaved. The sheer density of people means that anti social behaviour will get angrily shut down very quickly.

It can be non-sentient and still have an observable personality. The same way a character in a novel can have a personality despite not being real.

They do acknowledge this on the site

> Based on VOA data (Nov 2025) which is often inaccurate. Many pubs have also closed since then.

The bug-free code one feels unfalsifiable to me. How do you prove that 10,000 lines of code is bug-free, and then there's a million caveats about what a bug actually is and how we define one.

The second claim about novels seems obviously achieved to me. I just pasted a random obscure novel from project gutenberg into a file and asked claude questions about the characters, and then asked about the motivations of a random side-character. It gave a good answer, I'd recommend trying it yourself.

I agree with you but I'd point out that unless you've read the book it's difficult to know if the answer you got was accurate or it just kinda made it up. In my experience it makes stuff up.

Like, it behaves as if any answer is better than no answer.

So do humans asked to answer tests. The appropriate thing is to compare to human performance at the same task.

At most of these comprehension tasks, AI is already superhuman (in part because Gary picked scaled tasks that humans are surprisingly bad at).

You can't really compare to human performance because the failure modes and performance characteristics are so different.

In some instances you'll get results that are shockingly good (and in no time), in others you'll have a grueling experience going in circles over fundamental reasoning, where you'd probably fire any person on the spot for having that kind of a discussion chain.

And there's no learning between sessions or subject area mastery - results on the same topic can vary within same session (with relevant context included).

So if something is superhuman and subhuman a large percentage of time but there's no good way of telling which you'll get or how - the result isn't the average if you're trying to use the tool.

I've done similar loose experiments using a 19th century French novel I have read (L'Agonie by Jean Lombard), and which is quite obscure. There is no English translation of the novel published.

Using Gemini Notebooks I've found it passable at summarizing chapters, listing characters, major theme and so on, and it can do this in English.

"What is the symbolism of the Black Stone?"

> In the sources, the Black Stone (referred to as the Pierre-Noire) serves as the central religious icon of the Syrian Sun cult brought to Rome by the Emperor Elagabalus. Its symbolism is multifaceted, ranging from fertility and virility to a mystical pursuit of universal unity.

> It represents the perennity of the Sun, which fertilizes the world, causing "germs to rise" and spreading them through the atmosphere. It is viewed as the "definitive form" of divinity, intended to absorb and replace the "transitory forms" of all other Roman, Greek, Egyptian, and Persian gods, including the Christian "Kreistos". > Virility and Phallic Symbolism > > The sources explicitly characterize the Black Stone as a gigantic sacred phallus. It is described as: • An icon of virility and the "organ of generation" • A "unisexual icon" that materializes the generative force of nature • A representation of "virility in activity," which is why it is often paraded and elevated in an "orgasmic" or "colossal adoration"

> The Androgyne and Universal Unity - Beyond simple fertility, the philosopher Atillius explains a more complex, "mad" metaphysical project associated with the stone. It symbolizes "Life One" (Vie Une) and the return to a unisexual state of perfection. • The Androgyne: Atillius believes that by pursuing "the male sex by the male sex," the cult "inutilizes" the female sex to eventually create the Androgyne—a self-sufficient being containing both sexes • Unity: The stone signifies the fusion of all generative forces into a single Unity, reversing the "separation of the sexes" which is viewed as a state of unhappiness and impotence. • Marriage of Moon and Sun: The ritual marriage of the goddess Astaroth (representing the Moon and the female principle) to the Black Stone (representing the Sun and the male principle) symbolizes the merging of the Orient and Occident into this unified life principle > > Destruction of the Symbol - The Black Stone ultimately becomes a symbol of Oriental pollution and decadence to the Roman populace. During the final rebellion against Elagabalus, the stone is torn from its temple on the Palatine, defiled with filth, and broken into pieces to ensure that its "signification of Life" would never again dominate Rome.

This is all accurate to the book, even teasing out a couple themes that were only subconsciously present to me.

The NotebookLM version gives citations with links to the original text to support all these assertions, which largely are coherent with that purpose.

The input is raw images of a book scan! Imperfect as it is it still blows my mind. Not that long ago any kind of semantic search or analysis was a very hard AI problem.

Not quite the same analysis. The human is better, no surprise. But the NotebookLM output links back to the original book in a very useful way. If you think about it as fuzzy semantic search it's amazing. If you want an essay or even just creativity, yes it's lacking.

It doesn't have to be the same analysis to put it in a partially overlapping vector space. Not saying it wasn't a useful perspective shuffling in the vector space, but it definitely wasn't original.

LLMs haven't solved any of the 2029 predictions as they were posited. But I expect some will be reached by 2029. The AI hype acts like all this is easy. Not by 2029 doesn't mean impossible or even most of the way there.

LLMs will never achieve anything as long as any victory can be hand waved away with "in the training set". Somehow these models have condensed the entire internet down to a few TB's, yet people aren't backing up their terabytes of personal data down to a couple MB using this same tech...wonder why

It wasn't a hand wave. I gave an exact source, which OP admitted was better.

They certainly haven't "condensed the entire internet into a few TBs". People aren't backing up their personal data to a few MB because your assumption is false.

Maybe when people stop hand waving abilities that aren't there we will better understand their use as a tool and not magic.

Surely there is analysis available online in French though?

I think your comment was not written by an LLM.

Some people are going to spend 10 minutes refining a prompt to get a human looking 2 paragraphs message after rewriting half of it. Then they're going to be like GOTCHA I USED A LLM.

I go a step further than this, which is to make the beancount files 100% generated by a program - no manual edits allowed at all. I have a version-controlled directory with the raw data (csvs, pdfs, weird text formats) from a bunch of different sources (bank accounts, payslips, pension funds, mortgage statements, and stock market price data). The process is then just an ETL pipeline to an intermediate data structure. That data structure can be serialized to beancount format, hledger format, whatever. I've even had it output prometheus metrics so I can create nice dashboards in grafana.

I dump more raw data in every month, handle the 1-2 new edge cases in code, and voila: a complete, accurate, queryable, debuggable, visualizable, and fully reproducible history of my finances.

How do you deal with one of transactions? How do you assign them to the right account?

For checking accounts, I have a list of rules that each transaction passes through. If a rule matches it generates the double-entry transaction going from the checking account to the account listed in the rule (or vice versa if the amount is positive). Earlier rules take precedence over later rules. If no rule matches it errors and prints out the transaction so I can add a new rule.

The main account I use for day to day spending is Monzo, they correctly categorise 99% of my transactions for me (and this is included in the csv export) which makes this way easier.

> Other than Minecraft, can you name one successful game written in Java?

The other major one would be RuneScape.

Doing all this in an hour is such a good example of how absurdly efficient you can be with LLMs.

From reading the TIL, it doesn't appear as if Simon used LLM for a large portion of what he did; only the initial suggestion to check the archive, and the web tool to make his process reproducible. Also, if you read the script from his chat with Claude code, the prompt really does the heavy lifting.

Sure, the LLM fills in all the boilerplate and makes an easy-to-use, reproducible tool with loads of documentation, and credit for that. But is it not more accurate to say that Simon is absurdly efficient, LLM or sans LLM? :)