Do all the things like ++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatarSign Up
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple APILearn More
Search - "mapping"
I messaged a professor at MIT and surprisingly got a response back.
He told me that "generating primes deterministically is a solved problem" and he would be very surprised if what I wrote beat wheel factorization, but that he would be interested if it did.
It didnt when he messaged me.
It does now.
Tested on primes up to 26 digits.
Current time tends to be 1-100th to 2-100th of a second.
Seems to be steady.
First n=1million digits *always* returns false for composites, while for primes the rate is 56% true vs false, and now that I've made it faster, I'm fairly certain I can get it to 100% accuracy.
In fact what I'm thinking I'll do is generate a random semiprime using the suspected prime, map it over to some other factor tree using the variation on modular expotentiation several of us on devrant stumbled on, and then see if it still factors. If it does then we know the number in question is prime. And because we know the factor in question, the semiprime mapping function doesnt require any additional searching or iterations.
The false negative rate, I think goes to zero the larger the prime from what I can see. But it wont be an issue if I'm right about the accuracy being correctable.
I'd like to thank the professor for the challenge. He also shared a bunch of useful links.
That ones a rare bird.22
I think the sleep deprived me is finally cracking under the weight of incompetent assholes.
We just launched a major project in some weird cocktail of Agile slapped with MVP and release to the wild in a waterfall, but it was premature, premature in the sense QA hasn't even finished their side of things, but because some fuck with with "manager" in their title decided they have burnt through the budget with incompetence and scrapped an entire element of the project and outsourced just so they could make a shittier version that doesn't even fucking work.
How hard do you want to fail before you will start listening to the people that now have to work around the fucking clock to clean up this horse shit of a mess.
I'm literally arguing over field mapping with multiple 3rd parties, when the fucking requirements state WTF this is suppose to look like. All because they didn't validate or test their own shit.
Why is EVERY FUCKING cock head in this industry a waste of space and cash! Is it really to much to ask for 1 fucking project to fucking go live that actually fucking works where I don't need to work 2 weeks straight (including weekends) after going live just to be sure that what shit does hit the fan isn't going to create a SEV 1 issue...
Sorry, I'm pissed at the incompetence of others I need to deal with on a daily basis. It's not like this field is insanely hard. A little attention to detail and self validation, verification goes a long way. But clearly that's a rarity.
Once this shit is stable and actually works, I'll be pulling out the mop to clean up half this shit just so it actually works.
Oof, I'm getting to old for this bullshit.4
My God is map development insane. I had no idea.
For starters did you know there are a hundred different satellite map providers?
Just kidding, it's more than that.
Second there appears to be tens of thousands of people whos *entire* job is either analyzing map data, or making maps.
Hell this must be some people's whole *existence*. I am humbled.
I just got done grabbing basic land cover data for a neoscav style game spanning the u.s., when I came across the MRLC land cover data set.
One file was 17GB in size.
Worked out to 1px = 30 meters in their data set. I just need it at a one mile resolution, so I need it in 54px chunks, which I'll have to average, or find medians on, or do some sort of reduction.
Ecoregions.appspot.com actually has a pretty good data set but that's still manual. I ran it through gale and theres actually imperceptible thin line borders that share a separate *shade* of their region colors with the region itself, so I ran it through a mosaic effect, to remove the vast bulk of extraneous border colors, but I'll still have to hand remove the oceans if I go with image sources.
It's not that I havent done things involved like that before, naturally I'm insane. It's just involved.
The reason for editing out the oceans is because the oceans contain a metric boatload of shades of blue.
If I'm converting pixels to tiles, I have to break it down to one color per tile.
With the oceans, the boundary between the ocean and shore (not to mention depth information on the continental shelf) ends up sharing colors when I do a palette reduction, so that's a no-go. Of course I could build the palette bu hand, from sampling the map, and then just measure the distance of each sampled rgb color to that of every color in the palette, to see what color it primarily belongs to, but as it stands ecoregions coloring of the regions has some of them *really close* in rgb value as it is.
Now what I also could do is write a script to parse the shape files, construct polygons in sdl or love2d, and save it to a surface with simplified colors, and output that to bmp.
It's perfectly doable, but technically I'm on savings and supposed to be calling companies right now to see if I can get hired instead of being a bum :P20
The bouba/kiki effect is a non-arbitrary mapping between speech sounds and the visual shape of objects. It was first documented by Wolfgang Köhler in 1929 using nonsense words.
I fucked up. Recently I applied for a job in Intel. All questions they throw at me I answered well, but there's one question that f**ked me hard that I can't think of any answer to. (Because ! am not familiar with this)
I was questioned about SLAM ( Simultaneous localization and mapping), I am new to this.
Now I think I failed to get the job. Therefore, I f**ked up15
I just realised I have 1TB of MS OneDrive Cloud space lying around unused. DAMNNN!!!
Just yesterday, I was thinking of backing up all my content to cloud (because just in case and past experiences of losing data).
I did a quick fact check and figured that I have ~450 GB of unbacked data.
After quick calculations, I came to a number of how many Google accounts I'll need for 15 GB per account of drive space.
Today, I was playing around with my Microsoft Developer account and saw OneDrive. I thought let's check how much free space does MS Dev subscription offers.
It showed 1024 GB. FUCK! My balls dropped.
Now here's what I did...
I have a local drive of 500 GB, which holds all the unbacked data. Now I setup my local OneDrive there and put everything into OneDrive.
And then, I moved my local Google Drive into OneDrive. A nested setup for important stuff.
So this way, less important stuff is backed up on cloud and accessible everywhere.
And more important stuff gets synced on Google Drive and OneDrive, both.
Did I do the right and sensible thing with this kind of setup?
MS Developer subscription says they expire it in 90 days but until today, they have auto renewed it always.
I still have ~500 GB of space which can be consumed.
Also, overall MS ecosystem seems much better to me than Google. Moreover, MS allows custom domain mapping which Google doesn't.
Let's see how can I entirely migrate to MS ecosystem in near future.18
I fucking hate entity framework.
It turns 10 mins of work into fucking hours of stress and bloat and shit.
It’s the one thing in dotnet that I cannot fucking stand.
Literally did a bit of work in 10 mins (using ef I might add), but because it’s not the”ef way” I need to create an extra table/class and then fuck about mapping the relationship in a complicated way to do what I had just done in only a few lines of code with one table.
Spend over an hour trying to get it to understand the relationship before I gave up for the day. Fuck it6
I had to contact technical support for an API. I’m pretty sure I was emailing with a bot because I was getting all sorts of stupid replies.
Me: I’m using your SDK for language X. It’s returned null for some properties. In the user portal, I can see there are values for those properties for the transaction. I don’t know why I’m not receiving them on my end.
Tech Support: Hi! I see the following was sent in the API response. [Sends api response to me.] You can also go the the portal to see those values.
Me: Yeah, I know. You just repeated everything I wrote to you. I don’t want to go to the portal. I told you I want to figure out why your SDK doesn’t seem to map those properties correctly when I receive the api response.
TS: Let me look at the docs. I think you need to send the properties you want in your request in order to get them back in the reply from the api. Such as <property>value<property> in the xml message.
🤨 The docs do not say that. They don’t even imply that.
Me: What the fuck?! That makes absolutely no sense. We have already established that the api **is** returning values for those properties. I want to troubleshoot why your SDK is mapping them as NULL.
Who asked for RedDatabase and RedXpert? You guessed it - nobody 😑 It's a buggy Firebird and DBeaver domestic knock-off!
My student was assigned with making Flask app by "simple" requirements. But guess what? We can't figure out hecking RedDatabase?! Figures out that they sent incompatible *.fdb database file, on which we wasted entire 3 hours troubleshooting obscure error, while clean database doesn't cause any trouble.
Last error that completely drained us is following:
Reason: unsupported on-disk structure for file /var/rdb/test.fdb; found 12.3, support 12.2; IProvider::attachDatabase failed when loading mapping cache [SQLState:HY000, ISC error code:335544379]
So now, he basically recreates database by scheme on image. What also shady seems to me is that application also has to deployed on virtual OS which he can bring on USB stick or by cloud later.
It should be possible to prove the collatz conjecture by mapping the unit digit transitions between numbers, namely into a finite state machine. From there we could use predicates and quanitifiers to prove, by process of exclusion, that for any given combination of 10s digit and 1s digit, no number can transition to anything but whats specified in the state machine assuming that number equals x in x3+1 or x/2
Ipso facto, a series of equations proving by process of elimination, that state machines transitions are the only allowable ones, would prove the collatz conjecture by proving the fsm is a valid representation for any given integer N.
I'm actually working on it now but I don't know enough about modular arithmetic and predicate logic to write a proof. I just have the state diagrams on some dot matrix paper at the moment.
If anyone wants to beat me to it, feel free.
So for example any number ending in 13, will, after x3+1, end in 40.
Any number ending in 40 will end in 20. Any number ending in 20 will end in 10, which will end in 5 as the unit digit.
It's easier to prove in the single digit case, and the finite state machine for that is already written, at least on paper.
I'll post pictures when I get a chance.7
For some reason I always have a hard time mentally mapping "asc/desc" to dates. I think of stairs and mentally map the dates to unicode timestamps. Am I the only one? Sort descending by date is newest first, btw6
Make an ASP .NET application for job interview take home assignment.
Try to use docker with it.
Runs fine through Visual studio (not code)
I declare is working and submit to organization but say it can run through docker-compose up.
I get reply that even the basic command doesn't work.
Turns out visual studio does some magic mapping or caching under the hood that I couldn't find in any config in the project and somehow gets it to work, but when running without Visual studio it doesn't have that magic context shit and thus running through terminal fails.
Obviously a lot is my fault for assuming what works through IDE would run through terminal without testing, but I will be angry with VS to make myself feel better >.>2