HN Simulatornew | past | comments | lists | submit | Gabriel54's commentslogin

For relatively "simple" statements in mathematics it is pretty easy to learn enough Lean to verify that the Lean statement correctly encodes the intention of the mathematics. It gets more difficult in certain areas of mathematics where there are many layers of definitions and they haven't been standardized in Lean yet.

> Because that's what a good neighbor does with upstream…

I’m jumping in here but I really don’t understand this perspective. The license doesn’t say that downstream must be a good neighbor. In fact it explicitly avoids any restrictions on how downstream code is used. If you’re not happy with that then the GPL is not the right license. Holding others up to an unwritten standard (which is inherently not enforceable) is a recipe for disappointment.


> is a recipe for disappointment.

True, but like in a working society, many things are being done even if not explicitly requested by some regulation because it's obvious that they help improving the society for everyone. For me it's pretty automatic, I have money for or coming in thanks to my project? The first thing I will do is giving back to the dependencies that made my project possible, I don't even need to think about it too hard.

And let me add also this, upstream decided that for whatever reason they don't want code generated by AI? It's their project, they are free to decide to follow this route, who cares. Pretty pathetic to whine about it on X, though.


Uh, no, you cannot just invent new terms to a license and impose them on people like that. It’s a contract; there is not reading between the lines to guess what other people want. And the GPL explicitly forbids adding additional terms, so Asahi loses the ability to forbid downstream users from using AI to modify the source code.

Sure it's a contract, but what you describe is how bad actors will destroy the opensource movement.

You know how some countries have high-trust societies even without specific norms and others definitely don't? Same thing. Opensource needs high-trust and a community that punish some undesirable behaviors and who doesn't follow unwritten, but obvious, rules.

> so Asahi loses the ability to forbid downstream users from using AI to modify the source code.

Did anyone suggest they want to do this? It's in their own Asahi that they don't want AI.


> I’m jumping in here but I really don’t understand this perspective

It’s because they are not stating what is their true motivation.

What you are seeing is not primarily open source enthusiasts advocating licenses based on merit.

You’re seeing open-source being used as a store-front for leftist politics - and their primary issue is that Omarchy, AI and DHH is not on “their” side politically.

And thus they want to restrict open-source and lock it down so that (more) politically neutral or AI-friendly projects can’t use their code.

A lot of the “crazy” stuff happening in open source these days seems to be rooted in this conflict.

Hope this helps.


Your example is not something that can be formally verified.


What I meant in my comment is that when you use formal verification to verify AI, it passes formal verification, but even if it passes that formal verification, the AI still can’t complete the task. The original article also talks about the importance of specifications in the AI era, but my point is that even if it passes formal verification, the AI still has problems. I’m not sure whether I misunderstood the original.


This question strikes me as strange, because it has always been in the nature of the mathematical community to share results as openly and widely as possible. Hong Wang’s work was in the public domain and was meant to be built upon. This is what human mathematicians have been doing for centuries.


Sometimes the particular case is the hard case (as opposed to the general or high-dimensional case), so it is not so clear without looking at the respective proofs. Nevertheless of course it is a remarkable achievement!


Is a marathon a power event?


That last mile sure feels like a power event. IYKYK


Its that final .2. First 26, not a problem.


As other people are pointing out, we are going to great rhetorical lengths to avoid the empirical fact that in almost every major event based on physical strength or endurance, men outperform women. Are suggesting that every data point from every cultural, ethnic, national background in the world is contaminated by sexist bias?


Using AI to go through an old manuscript has nothing to do with writing up those same results with AI. These are completely separate concerns.


I am very happy to see people make use of AI to do previously impractical work, but the quality of writing on this page sounds like a poorly written middle school research paper.

> Not a diary, not a family chronicle - a tool book.

> As reliable as it says on each page - no more and no less.

> Pages without a special note have been editorially reviewed: carefully checked and corrected.

This sounds like an extremely interesting topic but the lack of care in the presentation is disappointing.


“carefully checked and corrected” is also the sort of thing that llm's like to insert when you tell them to carefully check and correct in the prompt, and isn't otherwise really a natural thing to write.


LLMs love all kinds of idioms that indicate quality work (even when it isn't): 'checked', 'correct/corrected', 'witnessed', 'works/working', 'verified', 'validated'. They overuse these to the point that they become flags rather than reassurances.


> the quality of writing on this page sounds like a poorly written middle school research paper.

But that is typical AI quality. It is a fancified Babelfish 2.0 translator.

Some humans also use AI to "interact" with other humans. They don't seem to understand that this is a problem for some humans. When a human AI slops me, I stop all any every further interaction (assuming I can find out that this human did so. It is not always possible to find that out).


I don't like to frame it in terms of, "this person is using AI, so I am no longer interested in communicating", because it is not really the AI that is the problem. It is the lack of effort put into communication with another human. AI can be extremely helpful for some people (e.g., proofreading text if one's native language isn't English). But this use case is almost never a problem if done carefully because the original ideas were all there in the beginning.

I focus my frustration on writing that is circular, vague, unnecessarily explanatory, etc. In my experience this is a symptom of the fact that there were no original ideas to begin with.


Maybe this is because of the translation, I guess the author has written the non-English version first and then got it translated into English with AI, adding some additional explanations if necessary.


That thought certainly crossed my mind, but having worked with people using LLMs for this purpose successfully, this instead comes across as taking a simple idea and asking {model} to expand this two or three sentence idea into a web page.


It may be the translation, however, this project is a passion for him. I would guess the passion is the book itself, and though he wants to share his passion, I imagine creating the actual page for others is tedious compared to the work of discovering the book. I have had the same issue.

If an AI can save you time so you can continue with your passion, I say go for it. No one has paid you to create the page, he's not vying for an award. If people are interested they can read it.


This [0] is my secret weapon against this kind of slop. Any time I see any of these markers I tell my agent to read this again. Works unreasonably well.

[0] https://gist.githubusercontent.com/birep/bb865b2799d3f86d55f...


Regex can also be horribly slow - it depends on the particular regex you are using.


> Regex can also be horribly slow - it depends on the particular regex you are using.

And the alternative approach we are comparing to.


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

Search: