Which ones are you claiming have already been achieved?

My understanding of the current scorecard is that he's still technically correct, though I agree with you there is velocity heading towards some of these things being proven wrong by 2029.

For example, in the recent thread about LLMs and solving an Erdos problem I remember reading in the comments that it was confirmed there were multiple LLMs involved as well as an expert mathematician who was deciding what context to shuttle between them and helping formulate things.

Similarly, I've not yet heard of any non-expert Software Engineers creating 10,000+ lines of non-glue code that is bug-free. Even expert Engineers at Cloud Flare failed to create a bug-free OAuth library with Claude at the helm because some things are just extremely difficult to create without bugs even with experts in the loop.

▲

bspammer 3 hours ago | parent | next [-]

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.

▲

verse 3 hours ago | parent | next [-]

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.

	▲	evrydayhustling an hour ago \| parent [-]
		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).

▲

retrac 2 hours ago | parent | prev [-]

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.

▲

daveguy an hour ago | parent [-]

"quite obscure" doesn't mean there is nothing in the internet that directly addresses the question.

Here is an english analysis of the text that easily showed up in an internet search:

https://www.cantab.net/users/leonardo/Downloads/Varian%20Sym...

This source includes analysis of "the Black Stone."

▲

retrac an hour ago | parent [-]

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.

	▲	daveguy 39 minutes ago \| parent [-]
		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.

▲

stingrae 3 hours ago | parent | prev [-]

1 and 2 have been achieved.

4 is close, the interface needs some work to allow nontechnical people use it. (claude code)

▲

fxtentacle 3 hours ago | parent | next [-]

I strongly disagree. I’ve yet to find an AI that can reliably summarise emails, let alone understand nuance or sarcasm. And I just asked ChatGPT 5.2 to describe an Instagram image. It didn’t even get the easily OCR-able text correct. Plus it completely failed to mention anything sports or stadium related. But it was looking at a cliche baseball photo taken by an fan inside the stadium.

	▲	protocolture an hour ago \| parent [-]
		I have had ChatGPT read text in an image, give me a 100% accurate result, and then claim not to have the ability and to have guessed the previous result when I ask it to do it again.

▲

falloutx 3 hours ago | parent | prev [-]

I dispute 1 & 2 more than 4.

1) Is it actually watching a movie frame by frame or just searching about it and then giving you the answer?

2) Again can it handle very long novels, context windows are limited and it can easily miss something. Where is the proof for this?

4 is probably solved

4) This is more on predictor because this is easy to game. you can create some gibberish code with LLM today that is 10k lines long without issues. Even a non-technical user can do

▲

CjHuber 3 hours ago | parent [-]

I think all of those are terrible indicators, 1 and 2 for example only measure how well LLMs can handle long context sizes.

If a movie or novel is famous the training data is already full of commentary and interpretations of them.

If its something not in the training data, well I don't know many movies or books that use only motives that no other piece of content before them used, so interpreting based on what is similar in the training data still produces good results.

EDIT: With 1 I meant using a transcript of the Audio Description of the movie. If he really meant watch a movie I'd say thats even sillier because well of course we could get another Agent to first generate the Audio Description, which definitely is possible currently.

▲

zdragnar 3 hours ago | parent [-]

Just yesterday I saw an article about a police station's AI body cam summarizer mistakenly claim that a police officer turned into a frog during a call. What actually happened was that the cartoon "princess and the frog" was playing in the background.

Sure, another model might have gotten it right, but I think the prediction was made less in the sense of "this will happen at least once" and more of "this will not be an uncommon capability".

When the quality is this low (or variable depending on model) I'm not too sure I'd qualify it as a larger issue than mere context size.

	▲	CjHuber 3 hours ago \| parent [-]
		My point was not that those video to text models are good like they are used for example in that case, but more generally I was referring to that list of indicators. Like surely when analysing a movie it is alright if some things are misunderstood by it, especially as the amount of misunderstanding can be decreased a lot. That AI body camera surely is optimized on speed and inference cost. but if you give an agent 10 1s images along with the transcript of that period and the full prior transcript, and give it reasoning capabilities, it would take almost endlessy for that movie to process but the result surely will be much better than the body cameras. After all the indicator talks about "AI" in general so judge a model not optimized for capability but something else to measure on that indicator