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

I can't figure this out from the website, does the text variant have tabular figures?


Activating stylistic set 01 (= script variant) does not effect the look of figures. You can try it out here on our website: https://www.monolisa.dev/tester/code


for the Monolisa folks here, I’d love to know too.


They're probably worried about liability. Let's say that Oracle finds out you reverse engineered their DB using Gemini. You can be sure they will sue Google. Not just for providing the tools, but you could make the argument that it's actually Gemini doing the reverse engineering, and on Google's hardware no less.


Let's say that Oracle finds out you reverse engineered their DB using IDA Pro. Would you expect Oracle to sue Hex Rays?

I don't understand why everything changes as soon as an LLM is involved. An LLM is just software.


The difference is IDA Pro doesn’t do something unless you instruct it to, an LLM is unpredictable and may end up performing an action you did not intend. I see it often, it presents me options and does wait for my response, just starts doing what it thinks I want.


This. It's going to be tricky for the frontier model labs to argue they didn't intentionally design their models to do so, when the models take illegal actions.

I'm not even sure how one would construct a viable legal argument around that for SOTA models + harnesses, given the amount of creative choices that go into building them.

It'd be something like "Yes, we spent billions of dollars and thousands of person-hours creating these things, but none of that creative effort was responsible for or influenced this particular illegal choice the model made."

And they're caught between a rock and a hard place, because if they cripple initiative, they kill their agentic utility.

Ultimately, this will take a DMCA Section 512-like safe harbor law to definitively clear up: making it clear that outcomes from LLMs are the responsibility of their prompting users, even if the LLM produces unintended actions.


> I'm not even sure how one would construct a viable legal argument around that for SOTA models + harnesses, given the amount of creative choices that go into building them.

I'm not a lawyer, but to me the legal case seems pretty obvious. "We spent billions of dollars creating this thing to be a good programmer, but we did not intend for it to reverse engineer Oracle's database. No creative effort was spent making it good at reverse engineering Oracle's database. The model reverse-engineered Oracle's database because the user directed it to do so."

If merely fine-tuning an LLM to be good at reverse engineering is enough to be found liable when a user does something illegal, what does that mean for torrent clients?


> No creative effort was spent making it good at reverse engineering Oracle's database.

That's the bit that's going to be nasty in evidence. 'So you didn't have any reverse engineering in your training or testing sets?'


Reverse engineering skill is just a byproduct of programming skill. They go hand in hand.


Yes.

Which is going to be hard to explain to a judge and jury, if it comes to that, how despite investing time, money, and effort (and no doubt test cases) into making a model better at reverse engineering... they shouldn't be liable when that model is used for reverse engineering.

Afaik, liability typically turns on intentional development of a product capability.

And there's no way in hell I'd take a bet against the frontier labs having reverse engineering training data, validation / test cases, and internal communications specifically talking about reverse engineering.


> “making it clear that outcomes from LLMs are the responsibility of their prompting users, even if the LLM produces unintended actions”

So if I ask “how does a real world production quality database implement indexes?” And it says “I disassembled Oracle and it does XYZ” then I am liable and owe Oracle a zillion dollars?

Whereas if I caveat “you may look at the PostgreSQL or SQLite or other free database engine source code, or industry studies, academic papers; you may not disassemble anything or touch any commercial software” - if it does, I’m still liable?

Who would dare use an LLM for anything in those circumstances?


If they thought they would succeed, no doubt oracle would sue. I expect bad behavior from multinationals, especially oracle


They would not even expect it to succeed, just make an example of the company (the lawsuit is the punishment) to discourage others.


We need that lawsuit to happen already so we can establish precedent. The person in the driver's seat of the Tesla should be at fault. The engineer using the llm should be at fault. The person behind the gun not the manufacturer should be at fault.


We shouldn't need a lawsuit. The legislative branch should pass a law clarifying those things, that's their job.


Then you need a lawsuit to determine whether the law is “constitutional”.


> The person in the driver's seat of the Tesla should be at fault.

I don't think this is a good analogy. For Tesla right now it might fly. However, when their software gets to waymo level of autonomy, I would expect liability to shift to the manufacturer.

If anything, I think that would be the true proof of a company trusting their software to allow for autonomous driving


> However, when their software gets to waymo level of autonomy

Luckily that won’t happen.


Also especially if they claim they're selling autonomous cars


I believe that Mercedes does offer manufacturer liability.


In the America, whoever has the most money is liable. It's not worth it for the legal industry otherwise. The lawyer earns his pay by convincing the court that whatever established precedent doesn't apply to his case.


Unfortunately.


Also because Google is the one with a lot more money than whoever was using Gemini.


they're very worried about liability, it used to be a small thing, now it's as important as being on the frontier

sad to see, bc China doesn't give a fuck about liability, this is a structural disadvantage

the labs don't feel very protected by government, meanwhile the chinese government is yet again fostering protectionism

american industry keeps getting fucked by dubious lawmakers


> Note this page includes affiliate links. [Amazon will earn less money if you use these links]

Ha ha. I never thought of that as a selling point for affiliate links. I suppose Amazon will make less money if people print their own books as well.


What I really want to see from a "*-programming-language" post on HN is _why_. Why Lily?


I am curious as well. some past readme has Why sections and I am not sure why they are removed/changed

this have "Why" section https://gitlab.com/FascinatedBox/lily/-/blob/d3ace2907747106...

this have "How Lily stands out from other languages:" section https://gitlab.com/FascinatedBox/lily/-/blob/785a88534cced53...


> More importantly, this design makes it easy to compose whole programs that will never be paused by a garbage collection by avoiding cyclical structures.

Or by "breaking" cycles, which will trigger the reference count deallocation.


The README on gitlab at least has a sentence or two on that: https://gitlab.com/FascinatedBox/lily

> An interpreted language with a focus on expressiveness and type safety

Personally I think typed scripting languages could be the future. They should support AOT compilation where necessary.


F# and C# are typed scripting languages. F# is quite similar to python in script form (.fsx), and has OCamls expressiveness, exhaustive pattern matching, and type inference. That results in highly expressive, terse, and ergonomic domain code.

The .Net VM now supports AOT compilation.

The future is now-ish :)


Why do you think that's the future?

Isn't a waste to essentially reinterpret an entire program that may be run 5000 times a day?

AOT compilation, how is that different than make && run?

At some point, you have a compiled language, if it's quick to compile, you're doing the AOT yourself, the scripting is an illusion. Pun intended.


Isn't it a waste to run a test suite for a program that would run 1M times a day in production?

The key adjective here is successfully run. You want to detect any errors as early as possible. Ideally even at the early stages of writing the script, when a typechecker is already able to point at certain errors, and thus help avoid missteps in further design.


> Isn't a waste to essentially reinterpret an entire program that may be run 5000 times a day?

This is a dated prejudice that I shared.

To get started coding with AI I made a dozen language comparison project for a toy math problem. F# floored me with how fast it was, nearly edging out C and Rust on my leaderboard, twice as fast as OCaml, and faster than various compiled languages.

Compiling could in principle be fastest, if we had compilers that profiled hours of execution before optimizing code, and only then for "stable" problems. No one writes a compiler like this. In practice, Just In Time interpreters are getting all the love, and it shows. They adapt to the computation. My dated prejudice did not allow for this.


a statically typed aot compiled scripting language is... not


Luau gets pretty close to statically typed and AOT compiled now. It's still a scripting language.

Even C or Rust can be a scripting language. You just integrate the toolchain to your app, same as every other scripting language.


+1 for Luau which is just realy good.


I script with Rust via cargo-script, it works great. Scripting is a task for when you want to achieve something in one file instead of a full blown application. It is not about the language, you can script in C or assembly if you so chose.


"Scripting" is a role: an embedded, human-friendly, compact language, also suitable for interactive work / REPL.

(Laugh all you want, but Haskell has a rather nice REPL, and can work as a scripting language.)


> why

Building a program language is like poetry. Everyone does it at some point, just most of us know never to share it.


That just moves the question to "why is this one being shared" then. I don't think "because the authors didn't know better than to avoid sharing it like 'most of us'" is a particularly good answer.


From the link:

> Key features of Lily:

> Built-in template mode

> Embed/extend in C

> Single-inheritance classes

> Exceptions

> Generics

> Algebraic data types (with Option and Result predefined).


That’s what. Not why.


The why: because Lua, Python, JavaScript, Janet, etc lack many or all these features. And each of these features is known to make life easier for a human programmer.


Looking through that list of features, Ruby (the dynamic language I know best) has all but 1 built-in (and the other can be added with Gems). I'm guessing Python probably has them all too (but I don't know Python that well). They're pretty common. So the why still isn't clear.


Tell me more about Ruby generics….


Want to split hairs eh?

Duck typing achieves the same thing as "generics", just at runtime vs. compile time.


Generics are implicitly compile time checks.

It’s a willful misinterpretation to read otherwise.


Is Ruby easy to embed in a C program?


Yes -> https://mruby.org

It's also incredibly easy to extend the main Ruby implementation with C, C++, Odin, Zig, Rust, Fortran, etc... Literally a few lines.


The main Ruby implementation is also fairly easy to embed. It's just not easy to embed multiple MRI ruby instances in a single application, and it's also a lot bigger than mruby.


That was originally the point of Ruby


RPG Maker used to embed Ruby before it was cool (and before they switched to JS for web support).


The reason it exists is to provide those features when programming computers.


99.9% of the time it will be "just because"


midges can fly, so presumably they would hit the web at random points. as to why flying would be useful for the midges, if they consume biofilms on the surfaces, that's less clear. perhaps over time the midges will evolve away from flying and the spiders will have to adjust their strategy.


hmmm makes me wonder if you could train llms on gzipped text. would save a lot of tokens that way.


This is based on the Dear ImGui library/framework [0]. It's not intended, strictly speaking, for standard desktop applications. It's intended for applications that use 3d rendering, like games or CAD.

Although you could certainly use it as a desktop editor if you wanted to, I think the real value is in embedding.

[0] https://github.com/ocornut/imgui


Yes I am aware that IM UI's are popular for games - level editors etc.

Just nice to see other possibilities.


Or, concretely, migrating hoverflies. Interestingly they don't appear to be colonial.


You're referring to Evolution, seems to be a CGRA

https://news.ycombinator.com/item?id=44685050


Yes thank you, so many news these months.


Yes, apparently they've developed new names: Generator and Scorer. This feels a bit like "Tai's Model" https://news.ycombinator.com/item?id=17863514


Haha "Tai's Model" is absolutely hilarious, that gave me a good chuckle. I checked and it currently is cited 568 times.


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

Search: