Hacker Newsnew | past | comments | ask | show | jobs | submit | schleck8's commentslogin

> It won’t cure people with metastatic disease, but it will help a lot live better lives for longer.

Cancer is a problem that can be solved, and it needs to be solved asap. Cancer too often gets either relegated to "Actually, statistically it's very unlikely" by people who don't have it or stylized to the God of Death that unlike other illness we won't solve anytime soon. There is no time to be lost tackling with AI. Dario gets it. Had cancer himself and his father passed away from it.


The thing that makes cancer such a hard problem is that cancer is really a collection of diseases. There's, what, like over a hundred of them? And one organ can produce several unrelated cancers too. I do hope AI will actually be able to figure out the commonalities between all of them and a potential path for a possible even somewhat-universal solution, but I at least don't even know if a universal "cure" is even possible. Granted, my knowledge of biology with respect to cancers is pretty limited.

Cancer is a mutation of cells. There might be 100 known cancers that present in humans, but in theory any mutation can lead to cancer.

Unless we can reliably sign our cells like we do our binaries, we ain't "solving" cancer.


This is exactly the mindset I meant. Look up how people dismissed Neuralink 5 years ago and now it's precise enough to play GTA via. A month ago Tao prognosed that the Riemann hypothesis will be solved in the next 25 years.

It's always impossible until it's done


I think you misunderstood what youre replying to. They're not saying cancers aren't worth fighting, they're saying cancer is not one thing. Theyre replying to the thread that started with "cancer needs to be solved asap", which isnt true or possible because The Cancer Disease doesn't exist.

Citation on neuralink?


So the citation... comes from the company itself?

https://www.youtube.com/shorts/wLkKKdBHdi4

I believe this is the GTA VI comment



What's your sense for FTL without time dilation effects?

I mean I get you but the problems you mention are specific to this Earth based middle ground we emerged into.

Others are likely so fundamentally linked to forces we cannot overpower due to the immense amount of variables in physical reality.

Consider a Riemann proof as text is a tiny amount of information relative to all the radiation and stuff floating in space or jiggle at the quantum scale.

Same with a neuralink + brain as our meat suits only want to make sense of things that are familiar.

Cosmic and quantum scale is way different than this stable middle ground we live in. We can still do a lot to stabilize here but I doubt things like space colonization work out given we cannot predict enough of the future to avoid the single catastrophic event that will end all progress and force a do over; Earth's resources can only support giving is so many mulligans. I see limited resources/time as another example of scaling laws just applied across eons.

Even though it's far more far fetched it's probably a better long term goal to focus on Stargate or The Expanse like gate technology rather than chew up Earth's resources chasing Star Trek ships.


You’ve taken the opportunity to glaze Amodei and now Musk in this unrelated thread. Perhaps we can celebrate the actual human researchers and doctors who made this advance.

You know BCI was a lively and progressing field before musk ever touched it, right?

And that BCIs have been used for people to play videogames literally since videogames were invented?

Neuralink is a refinement in the field, not a revolution.

edit: Watch the video shared in sibling comments. The big difference in neuralink from BCI SOTA in 1990 is a smaller set of hardware reading your brain (genuine improvement), configurability (minor improvement), and I think a significant improvement in fidelity. The implementation of thinking about moving a body part to give a reader a trivial muscle neural signal to read is older than I am, and has not improved as far as I can tell. That said, the user is demonstrating fine control of a game, so if those advancements were what it took to go from playing Civilization to playing GTA, kudos.

BCIs however are zero percent of the way towards anything like "scanning" your brain or "uploading" your brain, concepts that themselves might not even be physically possible. Even if you could magically copy your brain signals to a computer a la moving a VM, you would not be uploaded to the computer. A clone of your experience would. You still die in misery.

Unfortunately, the primary value Musk brought to the field was a willingness to invest money. Time and time again, his cultish supporters mistake a banal investment in engineering as groundbreaking, because they completely ignore the total lack of investment before he waved his cash around. We don't need musk to invest in things. We need a willingness to spend money towards goals. Also maybe read some magazines. BCIs were something Popular Science talked about occasionally, which is one of the ways I know about prior art in the field.


Well solving the 100 we very well could be solving cancer for 99.5% of folks while still not “solving” cancer.

300 answers to unsolved problems were dropped all at once by a frontier lab

there doesn’t even need to be a commonality, all will get solved

I hear ML researchers are even picking up smoking again


There is a key difference between what AI has solved so far and most types of cancer: A digital representation that can be manipulated as a surrogate.

For many cancers we don’t have a good animal model or cell model, let alone a simulation.

AI can and will help us identify good targets for treatment, but the learning loop will be full of slow non deterministic biomedical experiments.


I suspect it will take far fewer of those experiments for AI to develop a good simulation model of the phenomena at work than it has historically takens for humans to be able to understand and characterize it. Anthropic is already working on this: they're building a wet lab where researchers will conduct Claude-designed experiments. It really is kinda like Aperture Science, which (for me) is a source of both awe and concern.

This is satire, right? We're in a thread that says "wow, for once no hyperbole" - which one cannot help but associate with the lack of AI references in the article - and here we are a few comments deep with breathless AI hyperbole. Complete with cult personality worship.

I can't tell anymore.

I understand it's hard to burn through an 8-figure marketing budget but this is wild.


AI is dancing and sparkling its way towards solutions we've struggled with for decades if not centuries. That's not hyperbole; it's the reality we're currently dealing with. It portends both unimaginable well-being for us all (or at least those who could still afford it) as well as a complete deflation of our sense of purpose besides merely existing and keeping the machine's data troughs fed.

The commonality on all of AI's huge accomplishments so far is fast feedback, immediately verifiably true (assuming you trust Lean) answers. It is very far from being able to make the claim that it can do the same in clinical research.

>AI is dancing and sparkling its way towards solutions we've struggled with for decades if not centuries

In math.


Are you referencing something like Riemann hypothesis, which it came out 6 hours later someone had already written a proof for with zero AI? I think AI is great and will have its use cases, but I think your drinking the kool-aid a bit too much.

The human-written proof is not verified and contains several errors, it's not unlikely that there is one that breaks the whole proof because this has happened plenty of times for Riemann.

The Alpöge/Claude one is already verified.


Masullo's proof has severe flaws in it. The Claude proof has been mechanically checked and found to be valid (with respect to the produced Lean formalization).

Nope, I’ve drank the koolaid,

I’ve seen some of what’s going on with “long horizon” training and how it’s being applied to life sciences

I can extrapolate what that means and it bolsters my confidence into what I wrote


For starters, you might want to do some research into the origins of that expression.

yeah cultists march towards their self inflected death as they actually drank poisonous liquid

e/acc


Honestly with all the bad press, I'm still determined and hope for a better future where this becomes reality. I just hope the focus shifts towards that, it would be an incredible achievement.

Cancer can be solved, and that's one thing I agree with Dario on. (His scare tactics and gatekeeping on the other hand actually slow down research.)

Agreed, if this was Dario's priority then there have been numerous missteps along the way that did more harm than good.

Its actually crazy all of these threads end up being about how good AI is, when the post has 0 to do with AI.


need help

Did this comment get cut off, or maybe you replied to the wrong one?

Which cancer? I ask because the specific thing preventing “a cancer cure” is the fact that cancers are only vaguely related. It’s like saying “broken bone is a problem that can be solved.”

Yes, it can, but to imply it’s simply one disease is missing completely the exact reason why it’s so hard to cure.


If you have a physics background and want to contribute to breakthroughs like this, check Physlib (counterpart to Lean's Mathlib).

It's making quick progress and is part of the Lean community.

https://physlib.io


Also there is CS Lib for tcs.

https://www.cslib.io


is this the part where we definitively prove or disprove the existence of dark matter?

I thought that dark matter could be summed up as: we definitely know it exists (due to a wide range of observational data), we just have no idea what it is

As far as my knowledge goes, dark matter is just: well, from redshift/blueshift, we estimate the relative speed of astral bodies. Then, using Kepler's third law, (m+M)=distance^3/orbital period ^2, we estimate the mass. There's then a huge discrepancy, given that with that mass and that velocity, stuff would just shoot out of their orbits. For that we use the virial theorem, which states that in a stable system, 2kinetic energy= npotential energy, where n is such that the potential at a distance r equals a constant times r^n. If we adjust the mass so that it fits, we find that the mass we observe in a system and the mass that's actually present is off by a factor 5 to 6. So essentially, there's no doubt that dark matter exists, it just doesn't react to light the way classical matter does so we cannot observe it visually.

„just“

you can't formalize physics

why not?

Because experiments are ground truth.

They're only half right. The formalization of physics is called Hilbert's Sixth Problem[0] and there has been progress formalizing specific subdomains just fine for practical purposes.

But there's no unified theory, as quantum field theory and relativity don't get along and we still need a model for quantum gravity. So it's not possible to formalize the whole system because we genuinely don't know how the whole system works to form it's axioms.

[0] https://en.wikipedia.org/wiki/Hilbert%27s_sixth_problem


no I'm fully right.

You cannot formalize physics (and that's not what Hilbert's 6th problem is about). You can formalize some physical theories, but that's not the same as formalizing physics.

Physics isn't mathematics with different axioms. The ground truth is nature, not some axioms you need to fulfill. A formally verified theory can turn out to be physically wrong.

Just as an example because I see they suggest it as a project on their page:

I can formalize a tight binding Hamiltonian of graphene. I can write it down and then prove that this structure of the Hamiltonian means I get real eigenvalues, distributed symmetrically around 0, I get the [Dirac cone](https://en.wikipedia.org/wiki/Dirac_cone) at specific high symmetry points in momentum space etc. but at no point can I prove that this is actually a good/realistic model for graphene.

I could have chosen a very different Hamiltonian that includes spin orbit coupling or electron-electron interactions or different atomic orbitals or couplings to atoms further away etc. pp.

The only verification that can tell me which choice is a good one (not a correct/True one because you just don't have that in physics) is an experiment.


> You cannot formalize physics (and that's not what Hilbert's 6th problem is about). You can formalize some physical theories, but that's not the same as formalizing physics.

Yes, it is a totally correct statement, but the thing is we are talking English, and in English the word "physics" can mean either "a collection of physics theories" or "the underlying reality these theories describe". The exact meaning depends on the context. Your statement provides a context to interpret "physics" in the latter sense. "Formalizing physics" definitely asks for the former meaning of the word "physics".

So, while you are totally correct, it doesn't mean that you've proven that formalizing physics is impossible. Quite the contrary, you claimed that one can formalize physics (in the meaning "some physical theories").

> The only verification that can tell me which choice is a good one (not a correct/True one because you just don't have that in physics) is an experiment.

I'm not into the project of formalizing physics, so I don't know how they choose their terminology, but if it was me choosing it... First, I'd chose "physics" and "the reality" to avoid using "physics" as referent to both. Second, I'd say that any "formalized physical proof" is true. I'm not sure how words I'd choose to talk about correctness of predictions of physical statements/theories. Maybe "empirical validity"? Why to invent a terminological bicycle if it was invented already? Though, maybe physics uses some other terms for that? If so, then we could stop talking about truth at all, and use "logically valid" to refer to statements that were formally proven.


If the universe is empirically demonstrated to be be a mathematical structure you can indeed formalize and derive physics from first principles. In this case empericism confirms the particular map is correct not that there is one. To me it is inconceivable how you get observed physics with stable laws and conservations everything is not a mathematical structure.

> If the universe is empirically demonstrated to be be a mathematical structure

Their point is you can't do that. And they're right - this is, famously, Popper's point. You can empirically demonstrate it's not some mathematical structure, but not the converse.


Since we don't know all of physics, I assume you're right.

But you probably can formalize our current understanding of physics, which seems useful?


That's exactly how Mathlib and Lean work, and apparently that was sufficient to solve two mathematical physics problems to a significant degree (NS fully, YM partially).

not with that attitude

Is there a biology equivalent?

I found one project that seems serious, called Ripple. It's based on Lean and has a preprint here. Funded by a research grant:

https://arxiv.org/html/2607.13531v2

> †Supported in part by NSTC (Taiwan) grant 113-2221-E-002-204-MY3.

It's not well known yet though, only has two GitHub stars.

https://github.com/zinan-huang/Ripple


There really aren't the level of formal models in biology that would are viable for empirical validation and formal verification

Biology is outside of mathematic's and logic's realms

Biology is just applied chemistry... https://xkcd.com/435/

Yes, high on the wishlist: quantumgravity, room temperature superconductivity, majorana quantum computing. Maybe physicists also should make their millennial list of open problems.

You just need to ragebait AI: "AI could never have a physics breakthrough!"

How about: a prize for the first AI lab to figure out how to build a warp drive.

We may or may not get FTL out of this, but in the mean time, it would give mathematicians and physicists some space to breathe.


Curious, what sort of prize would incentivize a $1T company to do anything it didn't already want to do? I reckon it'd be more effective to threaten to regulate them if they fail.

Hey Claude I want to colonize Mars. Figure it out make no mistakes.

Still have some Fable 5.2 usage to burn this week, so here you go: https://claude.ai/share/67c6258b-69c2-43e8-a64c-ed08606079e7 :P.

> Yes. Whatever the "Whiteboard" is.

That gave me a chuckle.


Those are great open physics problems but as far as formalization goes, I'd already be happy with a mathematically rigorous formulation of established physics, like the Standard Model. :-)

See also https://news.ycombinator.com/item?id=50220840


Hoping this births a textbook or two somehow.

On the one hand, I really look forward to progress in physics to enable Star Trek-like technologies, but on the other hand, I wonder if we should solve our global conflicts first.

I mean, wouldn't it be great if AI could lead us to a world of lasting peace, prosperity, and happiness?


The major source of global conflicts is the scarcity of resources. A breakthrough in physics+engineering that allowed anybody anywhere to produce usable energy (eg electricity) at will wouldn't guarantee a conflict-free world, but it would be the biggest step in that direction I could think of.

So true. Most major 20th/21st-century conflicts were about oil. With climate change looming, experts are predicting water wars.

The demand for energy is limitless, though. Technology will always scale to using everything that's available, if history is any witness. Unfortunately, energy is also the standout factor in the scale of our problems and defines the upper bound to the damage that can be wrought.

As great as it may be to have it in order to do what we want to do, energy is intrinsically, fantastically dangerous and must be handled with an amount of caution we have never been able to muster. I strongly believe that at-will energy production is all but guaranteed to destroy the world.


I posted a nearly identical comment and thought I was having a stroke reading yours because I didn't remember using the very similar but different wording you did, haha.

A rich country toppling a weak country doesn’t happen because the rich country is poor. It’s because of the institutional logic of profit maximization.

Just to say that it’s more than just scarcity of resources.


If you have infinite resources, profit is pointless.

>A breakthrough in physics+engineering that allowed anybody anywhere to produce usable energy (eg electricity) at will.

It's called solar power.

People are so enamored with their belief that AI can basically do magic and let them live in Star Trek that they forget solutions already exist for these problems.

We could already feed, clothe, provide clean water, clean energy, medical care and education to everyone on Earth with current technology.

We don't because, at scale, we don't want to. It's a problem with policy, culture and religion, with our primate minds being driven towards hierarchies of power and scarcity. If AI somehow made free energy available (which it won't because ye canna change the laws of physics captain), we still wouldn't want to.


There will always be a scarcity of resources given that local resources are finite and we can not travel faster than we can grow to fit our carrying capacity. Fundamentally human conflict is about competition to reproduce in a finite environment.

> I mean, wouldn't it be great if AI could lead us to a world of lasting peace, prosperity, and happiness?

Not convinced that is within the capabilities of any AI without it doing things we would in fact not want it to do to us as a species.

We seem to be built for conflict and I'm not sure that what is left when that is removed is still us.

> Let me tell you something about Hew-mons, Nephew. They're a wonderful, friendly people, as long as their bellies are full and their holosuites are working. But take away their creature comforts, deprive them of food, sleep, sonic showers, put their lives in jeopardy over an extended period of time and those same friendly, intelligent, wonderful people... will become as nasty and as violent as the most bloodthirsty Klingon. You don't believe me? Look at those faces. Look in their eyes. (Quark from the always brilliant DS9).

Yeah I'm cynical <waves at history>.


OK, I'll bite: I find little support in history for the theory that conflict is inevitable because humans have an intrinsic desire or inherent nature that drives us to go to war. War is what people have turned to in roughly two circumstances, none of which are or will be ubiquitously present:

1. when (the leaders of some) some belligerent tribe, nation or coalition etc perceive that they can promote their interests by going to war without risks that at first blush will outweigh the gains.

2. when some (the leaders of some) tribe, nation or coalition etc can credibly anticipate that they are about to be attacked and then go to war, because 'attack is the best defense'.

Proof abounds in history that war is not inevitable. One example: peoples all over Europe that used to engage in constant war with their neighbors in the next valley, next district, next-door nation, over hunting-, grazing-, market- and raw material opportunities have ceased to do so even if they are essentially the same peoples.

It's of course essentially just simple cost/benefit analysis, not blind human nature.


I'm becoming increasingly convinced that many/most of the "great men of history" were actually insufferable ignorant pricks with astounding luck and zero concern for ethics or morals. This is mostly based on observations of the contemporary world, and how startlingly true it currently is. There's no reason to assume the people of the past, whose exploits were recorded into history, were remarkably better/different.

It's probably not either/or.

Society and culture is downstream of economics, which is shaped by available technologies.

Warp drive may have started Star Trek's humanity on the path to utopia, but I'm pretty sure that it's the matter replicator that made it work.


I hope one day we would have formally verifiable governance structures that foster peace, prosperity, and happiness.

> wonder if we should solve our global conflicts first

Every endeavour takes resources. Thus a pragmatic approach would be to recognise that resources are limited, and best strategy is pick low-hanging fruit first.

FTL travel requires new physics. And even then (or if found impossible), for example interstellar travel would be a massive undertaking involving all of mankind. And may involve "generation ships". Let's leave that for another day.

Otoh, supplying clean drinking water to every inhabitant of this planet is doable, easy, cheap & would be gamechanging for many of the recipients. Lets do it!

It's easy to see that barriers blocking this, are political/religious in nature, not technical. And thus politicians & lobbyists are thrown at it.

In the meanwhile, doing the math on what would be needed to reach Proxima Centauri, could be (relatively) easy. So sure, give some people a laptop & office space to see if they can work it out.

TLDR; keep chipping away at whatever problems you encounter. Far-future or otherwise. But be sure to pick low-hanging fruit first. $ Cost is a reasonable proxy for this. If it's cheap, give it a shot.


I think global conflicts are largely due to scarcity and a desire for control over resources. If AI makes everything significantly more abundant, I think it would in turn massively reduce global conflicts.

And how do you propose to do that?

Let AI invent the Holodeck.

“All of humanity's problems stem from man's inability to sit quietly in a room alone.”

― Blaise Pascal


AI won‘t. AI as a project is asserting power into the hands of a handful owners of capital, at a time when global inequality was already a massive driver of conflict and harm to humanity in general. AI will only make this problem worse.

Additionally, look at how AI is used in global conflict today, e.g. its role in the Gaza genocide, and you must conclude that this technology does not have a good track record for global peace, quite the contrary.


Why not both at the same time?

Why not build space technologies to depart the global conflicts?

And go live where else? Mars is harsher than Antartica and warp drives depend on whether physics allows a feasible design that doesn't require too much energy. And even then, where is a habitable planet for humans out there?

Just outside of Earth's atmosphere, in a new colony station, then vacation on Mars in a bubble utopia paradise there. Baby steps :)

Below is a list of conflicts created, funded, armed, and backed by the USA. If you want to stop "global conflicts", you need to look in the mirror and understand who is the problem, before you propose any solutions, like stalling Physics research as a solution to global conflicts.

You need to have crystal clear clarity about who exactly is the Threat to the global peace.

  Argentina, 1976, CIA backed coup
  Brazil, 1964, CIA backed coup
  Bolivia, 1971, CIA backed coup
  Chile, 1973, CIA backed coup
  Cuba, 1950s, CIA backed Batista
  Dominican Republic, 1902–1924, US military occupation
  Ecuador, 1961, CIA backed coup
  El Salvador, 1980s, CIA funded dictatorship
  Grenada, 1979, CIA destabilised country
  Guatemala, 1954, CIA backed coup
  Haiti, 1915–1934, US military occupation
  Haiti, 1990, CIA backed coup
  Honduras, 1980s, CIA backed coup
  Nicaragua, 1979, US backed dictator
  Nicaragua, 1982–1989, CIA funded Contras
  Panama, 1941, US backed coup
  Panama, 1989, US military invasion
  Paraguay, 1954–1989, CIA funded dictatorship
  Peru, 1980–2000, CIA funded dictatorship
  Uruguay, 1973, CIA funded dictatorship
  Ghana, 1966, CIA backed coup
  Chad, 1982, CIA funded dictatorship
  DRC, 1961, CIA backed coup
  Philippines, 1965–1986, CIA funded dictatorship
  South Korea, 1945, Outlawed PRK government
  Cambodia, 1970, CIA backed coup
  Indonesia, 1965, CIA backed coup
  Laos, 1957, Multiple CIA coups
  Greece, 1947, CIA backed junta
  Italy, 1948–1996, CIA corrupted elections
  Iran, 1953, CIA backed coup
  Syria, 1949, CIA backed coup
  Syria, 2013, US drone strikes
  Niger & Sahel, 2013–2024, Counterterrorism drone deployments
  Somalia, 2013–2026, Airstrikes and raids
  Pakistan, 2013–2018, Covert drone strikes
  Iraq, 2014–2026, Counter ISIS intervention
  Syria, 2014–2026, Sustained military airstrikes
  Yemen & Red Sea, 2014–2026, Naval and airstrikes
  Libya, 2015–2019, Renewed bombing campaigns
  Bolivia, 2019, Disputed coup backing
  Iran, 2020–2026, Direct military strikes
  Gaza Sector, 2023-2026, US backed and armed genocide of Palestinians in Gaza
  Venezuela, 2025–2026, Raid capturing Maduro
  Nigeria, 2025–2026, Joint military operations
  Ecuador, 2026, Joint border airstrikes

based

on facts

Thank you comrade, complimentary vodka and lard will be delivered to you free of charge.

I see the pi=3 theorem missing, I'll add it.

You're thinking of engineeringlib. In physicslib it's 22/7

This is so strange. Perhaps it's recurrent depth. I don't think the new Anthropic models use it but GPT 6 does

Astra 6.2 is below Astra 6.

> Maybe a few centuries from now it would be thought of as barbaric that people we forced to sit on a desk for 8 hours a day just to afford a livelihood.

I'm fully convinced of this. It will probably be viewed in retrospect like we view the exploitative work during the Industrial Revolution, even if it seems like an exaggeration right now.


You don't need to verify 17 million lines of code, you just need to check that the hypothesis is formalized correctly (that's a subset) and that the kernel approves it

Perhaps read up on the value proposition of Lean.


There are still bugs in Lean and until those are fixed its approval is not final.

That's not how this is going to work, unless you are considering "final" to mean what convinces you.

And how many lines does that represent? More than will be reviewed still.

Half a page of code, so no.

You can cut off the appendix so it's roughly 500 pages long and Gemini 4 can digest it in one go (context window is around a million, this takes up around 300K tokens so it's inside the effective window).

This is only a subset of alleged errors, and not the problematic ones.

i agree with your first statement, not sure about your second (was this identified as a reparable error by any LLMs?)

The two claims are likely correct but not major flaws, they don't affect the most important part. But the latter seems to include several flaws too, most notably in theorem 11.1.2.1(2) on p. 480 onward.

Gemini 4 Neon and Opus 5.5 have also found several flaws that go beyond missing polish. I use Opus a lot for maths (different field so less than anecdotal evidence) and I trust it to atleast not be confidently wrong. It's conservative when making such claims without good backing.

Are you actually tying them to a theorem prover?

So that moves the goalpost to copyright being flawed in general I guess, since the same judiciary decided its precedents.

Maybe we should have had this discussion earlier. Why is there a system that Disney uses to cease-and-desist kindergardens over wall paintings that feature a 100 year old character, whose creator is dead? Why is the law more relaxed (read much shorter protection) in patents than in copyright, despite the former often requiring a higher upfront investment?


Idk I’m not a lawyer. Just saying it’s disingenuous to call something “extreme ideology” for coming from a layman’s understanding. AI backlash is real, lots of people feel that training AI on content without the creator’s permission is theft and not fair use

And a lot of people don't. Check public sentiment surveys. AI backlash is a US phenomenon, it's the polar opposite in many countries.

Ok, I never said it was the majority view. But it’s not extremist and you’ve failed to make any argument as to why it is

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: