The difference is that the lumber mill isn't giving the logging company all the information required to run a lumber mill and the logging company isn't turning around and selling said information to anyone for $200/mo.
In my scenario, the only way anthropic and openai are profitable entities if they directly absorb the capacities of the companies, the same way Amazon "basics" exist to absorb the generic consumer product levels.
I'm not pointing out they'll take your secrets and sell them to the competition. I'm pointing out they will _be_ your competition. The same way Amazon basics competes with it's business interests.
> Similar to zig, odin, and others, its basically just C with some syntax conveniences.
Extremely reductive and untrue. As someone who still writes/deals with C daily, there is room for a successor that still attempts to be a thin wrapper around an abstract CPU. The C type system and preprocessor has some glaring flaws that are not fixable in a backwards compatible way.
Yeah I'm sure there are some people who just want C with better syntax and faster compile times, for them I think it could be fine (assuming they don't need well tested 3rd party libs, an ecosystem, documentation, portability, or robust tooling).
I just meant as my general purpose goto language, I couldn't add to the roster. C++ is already filling that niche for me (except with all the aforementioned benefits), python for scripts, C# for a solid GC lang, there's just no place for a scrappy quirky lang with lots of sharp edges and no value propostion.
I'm just not sure why you would choose _this_ language for those needs. There are like 10 new langs that are all trying to be "the next C" and they all kinda suck (Jai included). I dunno, for me none of them had the same kind of feeling that you get from the really top-tier languages, they all felt like "we took C and solved these annoyances" not "we had a fundamentally new vision".
Yeah, I find that a lack of a GC means that I don't reach for these languages unless I have a reason to think I really need that level of performance, you lose too many conveniences, the perf gains are usually not worth the investment of thinking through memory ownership. The only language of this class that I regularly use is D, in that lang I can remove all the GC parts for things that do have such perf reqs while reusing most of my GC code, but the things I can do with GC end up being really concise and easy to read, while still being faster than the equivalent python :shrug:.
To be fair to Jai, Odin and Zig, there are definitely software libraries/applications that the world would benefit from having, where this level of performance is basically required. The standard tends to be C++ these days (Rust is rapidly gaining ground, but it's still inconvenient in cases where you frequently need to abstract under the allocator), and I think everyone is looking for a way to not have to write c++ for this stuff.
For me Nim hits the sweet spot since 2.0 moved to ARC/ORC. All the benefits of GC for programming but it's much easier to control allocations and memory when desired. Plus I can run it as a script or compile to JS. I'd put Swift in a similar category too. Not compiling to JS but that it gives good control over memory while being automated via its ARC.
Interesting. I feel similarly but use Rust since I don't really have to think about GC or non GC, I use it more as a modern StandardML or OCaml but with much better performance.
No they are not equal. There are a lot of hairy details usually around byte layout/endianness that are defined (sometime implementation defined) that are UB or TBDB in rust. Also rust doesn’t have int overflow UB.
Often that’s just implementation defined behavior which is perfectly safe. You should just put some compilation guards to error out if someone tries to port your code.
C wasn't meant to fully replace low-level languages like Assembly. Context switching still isn't possible in C (nor in Zig).
And most C library calls are actually Unix system calls. Malloc() is an operating system call and not a library call. Yes, they made it a library call later on to facilitate usage in other operating systems but it was originally an integral part of the Unix OS.
Maybe it’s wishful thinking on my behalf, but I am still not convinced that LLMs are on a path to SciFi levels of apocalyptic malicious super intelligence. Rather LLMs at some level are just all of the humanity’s information rendered accessible in an unprecedented way.
In general trying to regulate information access is a losing battle that invites tyranny. So the goal should be minimal restrictions.
At the end of the day, the threats posed by capable AI tools have to be physical. I think the key threats are the following:
- Internet connected infrastructure being crippled
- Creation of WMDs
- Economic collapse (precipitous devaluation of knowledge work and IP).
I personally think the glory days of the wild west, mostly unregulated internet were already over before LLMs; and we need to take a step back to make something structurally secure. This (expensive) change would stop the irresponsible/malicious actor running a tireless hacking agent in a loop threat model. Even a rogue SciFi tier AI would have a much harder time escaping/propagating with a structurally secure internet.
Enabling WMD creation is scaring, but I don’t think it’s really that big of an issue. Anyone with a sophisticated enough supply chain to create AI data centers is leaps and bounds more advanced than what is required to enrich uranium or synthesize bio weapons. The problem is allowing access to untrusted parties. I think it’s fair enough that individual actors shouldn’t have unregulated access to all of human information (private frontier AI companies included).
The last problem is probably the trickiest, but again could probably be solved by regulation. IP protection is already tricky and I don’t think we should try to get more protectionist.
We really need to figure out how to preserve fulfilling careers (if AI does ever get cost effective enough). I don’t think, say accounting, is inherently more fulfilling than building a house. The problem is concentration of wealth and labor dynamics.
Of course all of this gets way harder if it proves that truly dangerous capabilities can be present in models that can be run on consumer hardware.
I don’t think it’s necessarily tyrannical to have a tier of hardware that’s labeled some equivalent of “weapons grade” and requires strict licensing. Restricted computers is a change from the norm. But I can go buy a shotgun with ease and not an F35 jet.
We’d just need to be careful that we can still have lightly to unregulated computing to a certain point and that access to the capable AIs isn’t restricted to just in groups.
reply