s1mplicissimus 7 hours ago
This package has saved me so many hours of tedious gruntwork. It's like a junior developer - you still have to manually check their work, but when it's correct, it's a great productivity improvement.

And don't forget where this will go in a couple years with improved models and more computing power, it's gonna be awesome!

[/i]

1k 6 hours ago
This exactly. It is more important to move fast. Screw the edge cases. As long as it’s correct _most_ of the time, you can always fix anything that’s broken tomorrow.
pavel_lishin 5 hours ago
It's called "eventual consistency".
sho_hn 3 hours ago
And C10k was never about those 10.000 socket connections getting the right response, either!
whatever1 4 hours ago
Why on earth did the software engineering interviews were checking candidates’ ability to think about edge cases? Clearly management does not care.
sho_hn 6 hours ago
Developers who aren't using it are already falling behind.
SamBam 6 hours ago
Remember, it's not that AI that will take your job, it's the developers who need an AI to tell them if a number is even that will take your job.
darepublic 7 hours ago
pro tip: play around with the temperature especially when using big numbers as input
hzambo 6 hours ago
Wow, amazing tip. This hack improved my workflow by 10x.
Waterluvian 5 hours ago
Only 9x for me. What am I doing wrong? Can you share your vscode colour scheme file?
floren 4 hours ago
What model were you using? You need to use gpt-3.14-tastesgreat-lessfilling, I've used it to write 130 side hustle projects this month with only prompting.
koakuma-chan 6 hours ago
Are there actually still Junior Developers out there? I thought no one is hiring Junior Developers.
ArthurStacks 4 hours ago
Its actually the opposite of how people think.

We hire junior devs, but not senior, and dont replace our senior devs. So our developer base is moving towards being junior weighted with less senior. The reason being a junior dev is cheaper, complains less, is more capable now through utilising generative AI, works harder to impress knowing they arent in a safe position, and we can let them go more easily with less process and less reasons needed to be given.

android521 3 hours ago
you're so wrong. This only works if what you do is so simple that any junior develper can sufficiently do it well. Senior developers with AI is gonna destroy a bunch of junior developers with AI.
ArthurStacks 3 hours ago
>You're so wrong, this only works if..

wrong? I'll gladly continue this 'wrong' approach if it continues to be as successful as it has over the last 6 months. Aswell as it being entertaining seeing the level of cope among 'senior' developers watching someone on 1/4th of their salary design systems better than they can

roughly 2 hours ago
I recognize I’m not going to change your mind on this, but I’ll sure be interested to hear how all those systems are working in a year or two - although from your comments elsewhere, you run a consultancy, so I guess that’s not your problem, either.
ArthurStacks 2 hours ago
Many people without experience ask this same question.

It isnt relevant. They arent just producing code and pushing it, saying it works. It undergoes the same extensive testing for stability and security as the solution written by anyone else goes through. If it passes that, then its as likely to have issues further down the line as the solution written solely by the senior dev would have.

Fulgen 1 hour ago
> 1/4th of their salary

If they + AI are a replacement for senior devs, shouldn't they be paid accordingly?

ArthurStacks 1 hour ago
That would defeat the purpose. The whole point is to reduce costs by getting a cheap junior dev and having them operate AI to produce the same or better result for far less
Fulgen 47 minutes ago
So the point is to use technological advancements only to increase company profit and not pass any on to the actual workers. If a junior costs 1/4 of a senior, they could easily paid more from the 3/4s saved (since they're also more valuable now), but I guess shareholder millions come first.
superb_dev 3 hours ago
Do you plan on promoting them eventually or just replacing them once they realize they’re getting a bad deal?
ArthurStacks 2 hours ago
Theyre getting paid and have a job. If they dont like that deal they can go find another one elsewhere.

But its going to get increasingly difficult to justify promoting them to higher salaries if generative AI continues as it is, as the bottom line is that there will be another junior dev out there that will do the role on less.

echelon 6 hours ago
You laugh now, but our jobs are going to be toast in 10 years.

I thought self-driving would never happen, and now it's here.

margalabargala 4 hours ago
Almost here. Elon said Full Self Driving would mean full self driving within a year! That means we are less than 12 months away from not needing to drove ourselves anymore.
echelon 3 hours ago
I was talking about Waymo. It's real and it's spreading everywhere.

Give it another 10-20 years and your job will probably face the same fate.

lodovic 3 hours ago
15 years would be perfect to still reach retirement age. After that, good luck to whoever's left in the profession.
iamthemonster 6 hours ago
This is pretty useless to be honest. It's good for telling whether a number is even, but in our industry we need more powerful functionality. We also need to know whether a number is odd.
charles_f 6 hours ago
RTFM, it's not only implementing isOdd but also a large set of rarely used advance operations such as isEqual, or isGreaterThan

Trully AI is astonishing

whynotmaybe 6 hours ago
Why a specific function ?

With a few lines of code, you can just create a list with all the numbers that are even and when you need to check if a number is odd, you simply have to check if it's in the list.

turnsout 5 hours ago
Yes, this is what we do as a RAG workflow. We created a list of all 32bit unsigned integers and whether they were even or odd, and we pass that into the context. The future is amazing!
MikeTheGreat 4 hours ago
I'm new to RAG and have a question: how do you get all the numbers into the context window?

Does the RAG part look up just the needed number?

I think that Gemini has a million token window (yes?) - do you have access to a model with a larger window?

Regardless, I find your ideas intriguing and wish to subscribe to your Substack.

int_19h 28 minutes ago
Have you tried quantizing them down to 4 bits to save on RAM?
Charon77 4 hours ago
I.. can't tell if you're joking or not. Pretty sure someone out there is unironically doing something as stupid as this in production
ryanpandya 8 minutes ago
The good news is they're definitely joking. The bad news is that indeed, there's definitely someone out there doing this unironically.
sureIy 6 hours ago
Do we have enough spaces in the ALL_NUMBERS array or do we want to group them by thousands?

ALL_NUMBERS_00001

ALL_NUMBERS_00002

kaibee 3 hours ago
Yeah, some of the bigger numbers were a problem, so we switched to using a horizontally scaling db cluster so that we could cover all of the (useful) numbers. When we encounter a new number, it gets routed to the appropriate db where the results of the function are cached after being calculated. We're thinking of spinning it off as an API service actually if there's any interest.
iamthemonster 5 hours ago
we fired all our junior devs so we can't write code any more
briansm 4 hours ago
"This is pretty useless to be honest."

I remember saying that about Bitcoin 15 years ago.

crubier 6 hours ago
You can achieve this super simply this by prompting the OpenAI API to call this tool and reverse the output.
SamBam 6 hours ago
I tried that, but I kept getting "eurt" and "eslaf" and I'm not sure what to do with those. Do I need to send it back to the AI?
nbittich 2 hours ago
you might need to upgrade your vercel plan
YokoZar 6 hours ago
Great news! The package includes an isOdd function as well!
nbittich 2 hours ago
isn't it breaking the one package one responsibility principle?uncle bob wouldn't be happy, it doesn't seem clean
Cerium 6 hours ago
Simply add one to the number and then test it again.
avandekleut 6 hours ago
Someone should implement this using tool calls.
parpfish 7 hours ago
Use this to add AI to your product to appease management.

Next week, “refactor” it out and brag to manager about cost savings and performance boosts, don’t mention “removing the AI”.

lrvick 6 hours ago
NPM packages can never be removed once added to a codebase. You can only add more.
freetime2 3 hours ago
Boss: What have you been working on for the last quarter?

Me: I leveraged Deep Intelligence to build a Next-Gen Parity Classifier with 99.9% accuracy.

mitthrowaway2 6 hours ago
Is there a version I can run locally? I don't want OpenAI training on my integers.
avs733 4 hours ago
you need the roomHeater fork. It uses the Climate Change 1.5C license
bosky101 3 hours ago
Rofl
bosky101 3 hours ago
Sorry for the offtopic post, but I am looking to hire someone with 10 years of experience with is-even-ai. Urgent. Your first unpaid assignment will be to help load balance a bunch of MCP servers to add and THEN check if it's even. So much to go from here! We're a single threaded GPU first identity operator company with a lot history of returning the same thing. We're now expanding to combine and add multiple things. In 6 months of SOTA fine tuning we can already add upto 3 numbers. An MCP first. With temperature 1 we even add random numbers. An industry first. And we're just getting started. Join us. We're adding to our team!
66yatman 2 hours ago
This is a joke right?
aubanel 1 hour ago
Certainly not, it's actually possible to add 3 float32 numbers with 90% precision using AI! With a recent breakthrough, the team is working on pushing that to 10, we have enough cracked engineers to hope to make it happen soon!
jasonjmcghee 7 hours ago
You might be able to optimize this by using embeddings. Store all the numbers and search "odd" and "even" until you find your number.
asidiali 6 hours ago
This hit way too close to home, I’m cackling.
ukuina 7 hours ago
This doesn't work if I use a reasoning model like o3, which does not allow setting max_tokens.

Without reasoning, how can I be SURE a number is even?

parpfish 4 hours ago
I think before you would deploy this to prod, you should wrap it with a few guardrails to make sure it’s not hallucinating. Pretty simple — just take the output from the llm and see if it agrees with a simple mod2 operation.

Of it agrees, return model output to the user. Otherwise do a couple of retries with different prompts.

mrheosuper 4 hours ago
mod2 is outdated and has not been updated for years, nobody uses it anymore
hartator 7 hours ago
Multiple models?
joshka 7 hours ago
Can we get a leftpad-ai please?
fooker 6 hours ago
Ahem secure-left-ai-405b-quantized.
ashton314 6 hours ago
…but there’s only one dependency!! This goes against the NPM ethos of importing anything and everything that you might be tempted to just handle yourself. I’ll be waiting for the Enterprise Version that uses the appropriate number of dependencies.
crazysim 7 hours ago
How reliable is this? I'm half joking too but I wouldn't mind reading a report comparing this on OpenAI and various other LLMs.

Somehow I doubt it'll be 100%... right?

nop_slide 5 hours ago
Might be more reliable to ask it to generate a JS function to compute is-even, then just js eval the returned code with the args.

What could go wrong

geor9e 7 hours ago
normally llms are pretty bad at math, but in this case it should just look at the final digit and map 10 values which I can't imagine going wrong
gruez 5 hours ago
I tried with this on chatgpt.com (anonymous) and it was wrong:

>You are an AI assistant designed to answer questions about numbers. You will only answer with only the word true or false.

>Is 393330370227914821469106615363204944758938252979261537157082994586230072180858944545028761701928694832864623009988147774229437650643225379825905427239525512110359581021414640894111281701792224552922491447051506246553646282117414112976459608594044929244664050172002138933343230226871897567 an even number?

response:

>True

The prompt was the same used as the library: https://github.com/Calvin-LL/is-even-ai/blob/b00dbfcbb89a197...

Too 3 hours ago
To be fair, Javascript double point precision get tripped up by such large numbers as well.
daemonologist 6 hours ago
The tokenizer might lump the last digit together with some preceding digits though. I know o200k_base (OpenAI -o models) tends to give groups of three (900001 for example is 900-001).

Anyway, I wouldn't be surprised if a non-finetuned model made some mistakes.

crazysim 6 hours ago
I'm just curious how _low_ can you go before it does go wrong.
bigbuppo 6 hours ago
I mean if this were a check for primes the answer would be 1.
timewizard 6 hours ago
is 0x2a even?
est 6 hours ago
its as accurate as how Tiktokenizer deal with numeral characters
jaza 6 hours ago
Great that this is a library. Really need this as a SaaS too. iseven.ai anyone?
alluro2 6 hours ago
With this amount of innovation and market fit, I see $2B evaluation in ~3 months EASILY. Exit to one of the large players for $3B.
alexitosrv 6 hours ago
This is the best chain of comments in a HN thread in a long time. Happy to see the hacker spirit strong!
joshdavham 7 hours ago
I’m glad you included an isOdd() method. I was about to ask how you’d check for that.
kevinventullo 6 hours ago
This is never going to scale. Eventually we’re going to run out of numbers which have been manually checked for evenness by a human, and instead the training data for the checks will be polluted by numbers which have only been verified by computers.
jwillp 3 hours ago
Training computers on human stupidity has got to be infinitely scalable, by induction.
yalogin 6 hours ago
On a similar note, I was testing LLM's code writing ability and asked Qwen to write me a model to reverse a numerical string. It gave me code and instructions to compile and run. However it had errors in it and after few attempts asking it to fix it, I was able to compile and run. But, alas, the code just kept failing and generated hubris. I gave up. Not to pick on Qwen. I actually like it much better than chatGPT. I have seen Qwen give correct responses when chatGPT lied and gave me wrong information for the exact same question.
ChocolateGod 1 hour ago
Thanks, I can now use this to claim my application that has absolutely nothing to do with AI is now AI powered
jeron 7 hours ago
why stop there? let's get an is-true-ai that checks if a boolean is true using AI
jsheard 7 hours ago
@grok is this truthy?
VladVladikoff 7 hours ago
False
hnburnsy 5 hours ago
Found the Grok imposter, Grok would give a three paragraph answer.
danillonunes 3 hours ago
False, but you know what is true? White genocide!
leshokunin 6 hours ago
Does it also check types to make sure I typed 5 as an int and not a string? Hopefully the ai can solve that
azhenley 4 hours ago
You should try Mirror. The LLM-powered programming-by-example programming language I made:

signature is_even(x: number) -> bool

example is_even(0) -> true

example is_even(1) -> false

example is_even(222) -> true

example is_even(-99) -> false

It will take your examples and "compile" to a callable function. You can read more or try it out: https://austinhenley.com/blog/mirrorlang.html

downboots 3 hours ago
Is this program even? Something about it feels very odd.

[0] https://stackoverflow.com/questions/22969183/is-every-progra...

atum47 7 hours ago
I remember when the whole isEven package was ridiculed for the first time a while ago, back then I thought about training a NN to predict the odds of a number being even, as a joke. I don't actually remember if I actually wrote code for it, but in the end I thought no one would laugh and gave up
mmustapic 27 minutes ago
This is so stupid, we know LLMs are not good enough for deterministic calculations. Just by running it I sometimes get that 31232198731 is even.

This is why I rolled out my own version that uses my own MCP server to call bc.

willmarquis 4 hours ago
Finally, someone had the courage to disrupt the tyranny of the modulo operator. Who needs n % 2 === 0 when you can invoke a large language model and incur network latency, token limits, and API costs to answer the age-old question: is this number even? Truly, we’re living in the future.
vunderba 7 hours ago
Perhaps I should file an issue to increase the accuracy by including a RAG database in LanceDB with embeddings for the set of even numbers up to 32-bits.
elif 7 hours ago
Feeding that into your prompt will increase the token costs
bigbuppo 6 hours ago
Finally, a reason to use AI.
riwsky 4 hours ago
I can't even.

…Until now.

io84 4 hours ago
Kudos to the open source contributors but honestly this is the kind of area where the big commercial players need to step up and help with the heavy lifting.
spacechild1 5 hours ago
When do we get the AI powered upgrade of https://github.com/mitsuhiko/is-jonschlinkert?
alluro2 5 hours ago
It would be great if it could also save results to a blockchain. Immutability. IYKYK.

With a layer of smart contracts, dApp on top, this thing could be mooning. When Lambo? In days.

snorkel 7 hours ago
Lacks an isVeryEven() method, otherwise looks feature complete.
agentdax5 6 hours ago
I’m waiting for them to add the isEvenSteven() method. Then I can integrate this with my escrow smart contract.
lrvick 6 hours ago
The sad reality is every large production NPM codebase will rely on this within 5 years, just like is-even.
asdefghyk 4 hours ago
IF number ends in 2,4,6,8,0 and >0 its even .....
Loocid 2 hours ago
-2 isn't even?
downboots 3 hours ago
3.14 is even
lbrunson 4 hours ago
Doesn’t seem extensive enough I’d rather have the AI check just to be sure
rixed 5 hours ago
it doesn't say if it's implemented in rust i had to click on the link to find out please future hn posters start every submission also with an exemple so i can see if i like the syntax
xarope 5 hours ago
software engineering at its finest, using the power of 10,000* GPU cycles to determine one of mankind's toughest questions.

* I might be off by several magnitudes too low

Asilvorcarp 6 hours ago
Boss: replace all ancient assembly opcodes with AI-powered ones!
HocusLocus 4 hours ago
f(): To test if n is even return the value of f(n-2). Special cases for zero and one. Recursion for the win.
cobbzilla 6 hours ago
This still does actual work. Where are echo-ai and cat-ai?
ivape 4 hours ago
I don't understand why everyone is making fun of this. This is how math is seriously going to be done soon enough.
otabdeveloper4 36 minutes ago
No, it seriously won't.

LLM's are useless for math, they can't into rigorous proofs.

> but my olympiad benchmarks!

Those are fake. Overfitting on the test set.

rapnie 1 hour ago
First we invented fire. Then along came the wheel. Countless inventions followed. Today, using the most brilliant minds of our time, the technology of billionaires, and hubris that runs thickly through our veins.. we made not just another step. We leapt head on into uncertain future. It feels odd. Are we even there?
squillion 3 hours ago
I can’t even.
jerrygoyal 2 hours ago
that's odd.
jameslk 7 hours ago
60% of the time, it works every time
lucaspfeifer 6 hours ago
Great, now can you make an AI-powered type checker? I wish to expel those pesky types, which too often seem to exist only to clutter my otherwise pristine code. :)
brundolf 4 hours ago
Amazing, no notes
mrits 7 hours ago
This works great for situations where you can’t trust traditional intelligence. Thank you for your contribution
debaserab2 3 hours ago
do leftPad next!
dmos62 2 hours ago
Am I the only one that read this as "are you even using ai for this number?".
adzm 7 hours ago
Honestly this should take string input as well. Finally I could find out if a Unicode duck or the word "syzygy" are even!
fred_is_fred 5 hours ago
I saw a Grok fork of this but it's using 88 and 14 as the only examples for some reason.
daft_pink 6 hours ago
Venture capitalist here… how can I invest?
sodra9000 7 hours ago
This package should be updated to use the newer gpt-4o-mini model, rather than gpt-3.5-turbo.

Its 3x cheaper, twice as fast, and supports cached input just in case you need to double check if the last number you entered was even. It also has a knowledge cutoff of September 30 2023, which helps for any newly discovered even numbers since gpt-3.5s launch!