"Super tinny monotone robotic voice" does not sound neither tinny nor monotone. Compared to what TTS from 90s sounded like. Or even how actors impersonated robots in movies. Has the model been eating too much hype DJs?
None of these examples are really what the prompt asked for. It's just like image models, once you get over how unbelievable it is that a computer produced this you realize the result isn't actually what you want.
Genuinely: how? Share some insights. So far I have seen anything exceeding about 2k lines of text in the context diverge. Meaning, throwing more LLM at it rapidly baloons the size at the expense of internal coherence. Things become stale, hallucinated, duplicated and outright faked. Only thing that works is constant manual intervention and pruning of the generated slop.
Not only these things are unable to find "best solution", they are unable to find any solution. Instead (especially for Opus) they seem optimized to convince user that the task is accomplished.
I crafted my own /investigate skill. Think of it as a version of /grill-me where you propose an investigation and dig into it until you come up with a spec backed by evidence.
My investigation skill can create one, two, or dozens of probes with benchmarks. Once you're confident in the solution, you can plan and author the investigation, then execute it phase by phase.
Somehow we also have memory safety bugs everywhere, too. So real world shows bugs in C code are possible. What even is your argument? Real men write asm?
Hard to guess, it can go either way. If you will need to be in a syndicate to use non-sterilized models, that mac makes sense. But if there is mandatory registration of personal cyberarms, you risk going to mines once they check you purchases. You could try to play normie and pretend you simply wanted to show off, by keeping your actual work on external disk, but that leaves traces on system. Counting on someone in the Gap renting you gray iron works as long as you can swap credits. Still, this gear is tiny. Put it in your e-car, with uplink, and leave it at uncle's farm. Discreet.
It was a dark rainy night in Neo-Tokyo as Blake puffed on his vapor cartridge and watched the Mac dealers prowl below. Almost 15k Union Credits to get one of them to meet you in an e-cafe with a fully loaded M5, but man, the inference rush from one of those things was something else.
But I can ask 100 causally masked questions against common prefix, and get 100 answers, all in a single PP pass using any existing "classical" attention transformer model? Like, I had the impression that is what everyone was doing for classification already?
Is the difference "we did RL to tune logit distribution"? Because I really do not see anything new there. What is the difference?
ok, point camera at a screen. let's counter that by also taking 360° image with secondary camera. Ok build some props, let's add gps into it. fake gps. let's add inertial tracking and self-destruct on tamper.
Ok, but we really need a fake image, here is our badge, give us signing keys for special use case...
By narrow luck compiler writers so far have been the sane bunch, and have ignored C++ committee on many important points. Thus we still have explicitly non-conformant things like -fno-exceptions that lets one use C++ compiler on embedded.
But I wonder how long that can last, with the way C++ is going.
At one point, it will make practical sense to update codebase to some other language, rather than keep fighting this one
I have been saying that C++23, or maybe C++26 due to reflection, will eventually be the last standard that actually matters.
For a large number of C++ users, it boils down to what it offers beyond C, but not to the extent WG21 is driving it since C++20.
Also the major surviving three compilers have lost wind on their sails as the corporations sponsoring their development have switched focus to other compiled languages.
Other than the whole security debate, there are no features that would make C++ significantly better for LLVM, GCC, CLR, V8, CUDA,.. improvements.
In fact, some of those projects still require C++17.
If this sounds strange, how many care nowadays about ISO Fortran 2023, or ISO COBOL 2023, despite the amount of software written in them powering many busisesses, or Python libraries even, e.g. SciPy.
Or even with C, almost 20 years later many still reach out to C99, ignoring everything else.
Not to take away from your points; SciPy is now Fortran-free completely[0] (we are also requiring C++17 at most). NumPy never had it. BLAS is all C/Assembly in all optimized vendors. For LAPACK we are working on it [1].
Once there is enough pain, none of the talking points matter for any language. They don't and can't die but linger. I fear that time for C family might come in a decade which would be a shame given how magical Cpp compilers are, all that effort folks pouring in.
Not "this". By that logic most people do not need backups too. Rebuilding working service state after config change is non-trivial, requires using admin-only kernel interfaces, and said kernel does not care about these types of problems. Meaning average user ends up simply rebooting rather than trying to figure why enabling wifi makes printer stop working (and such). We cannot have network stuff controlled by multiple programs, because linux kernel is broken like that. This thing is the userspace part of the monolith.
reply