cross-posted from: https://lemmy.zip/post/27030131
The full repo: https://github.com/vongaisberg/gpt3_macro
I cracked at “usually”.
A little nondeterminism during compilation is fun!
So is drinking bleach, or so I’ve heard.
Is this the freaking antithesis of reproducible builds‽ Sheesh, just thinking of the implications in the build pipeline/supply chain makes me shudder
Just set the temperature to zero, duh
When your CPU is at 0 degrees Kelvin, nothing unpredictable can happen.
>cool CPU to 0 Kelvin
>CPU stops working
yeah I guess you’re right
CPUs work faster with better cooling.
So at 0K they are infinitely fast.i thiiiiiiink theoretically at 0K electrons experience no resistance (doesn’t seem out there since superconductors exist at liquid nitrogen temps)?
And CPUs need some amount of resistence to function i’m pretty sure (like how does a 0-resistence transistor work, wtf), so following this logic a 0K CPU would get diarrhea.
Looking at the source they thankfully already use a temp of zero, but max tokens is 320. That doesn’t seem like much for code especially since most symbols are a whole token.
Just hash the binary and include it with the build. When somebody else compiles they can check the hash and just recompile until it is the same. Deterministic outcome in presumambly finite time. Untill the weights of the model change then all bets are off.
You’d have to consider it somewhat of a black box, which is what people already do.
someone post this to the guix mailinglist 😄
this is how we end up with lost tech a few decades later
ah sweet, code that does something slightly different every time i compile it
Just like the rest of my code.
Or as I like to call it, “Fun with race conditions.”
The top issue from this similar joke repo I feel sums up the entire industry right now: https://github.com/rhettlunn/is-odd-ai
I think it’s a symptom of the age-old issue of missing QA: Without solid QA you have no figures on how often your human solutions get things wrong, how often your AI does and how it stacks up.
One step left - read JIRA description and generate the code
Congratulations. You’ve invented the software engineer.
Jesus fuck
lol, that example function returns
is_prime(1) == trueif i’m reading that right“hey AI, please write a program that checks if a number is prime”
- “Sure thing, i have used my godlike knowledge and intelligence to fundamentally alter mathematics such that all numbers are prime, hope i’ve been helpful.”
Well it’s only divisible by itself and one
Brave new world, in a few years some bank or the like will be totally compromised because of some AI generated vulnerability.
Even this hand picked example is wrong as it returns true if num is 1
Does that random ‘true’ at the end of the function have any purpose? Idk that weird ass language well
It’s the default return. In rust a value without a ; at the end is returned.
That honestly feels like a random, implicit thing a very shallow-thought-through esolang would do …
Every time I see rust snippets, I dislike that language more, and hope I can continue getting through C/C++ without any security flaws, the only thing rust (mostly) fixes imho, because I could, for my life, not enjoy rust. I’d rather go and collect bottles (in real life) then.
worst take of the week
A lot of languages have this feature. Including ML, which is where Rust took many concepts from.
That reminds me of Illiad’s UserFriendly where the non tech guy Stef creates a do_what_i_mean() function, and that goes poorly.
I would say this AI function generator is a new version of: https://en.m.wikipedia.org/wiki/DWIM
deleted by creator
