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
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.
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?
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?
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.
> 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
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.
> 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.
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.
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.
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.
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.
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.
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.
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.
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.