Disappointed. I thought it was gonna be an API that serves profanity.

@ShadowOcto

23 күн бұрын

fr 😢

@wlockuz4467

23 күн бұрын

Ferb, I know what we're building today!

@unbiasedperson1155

23 күн бұрын

Okay ,let's build an open source profanity maker that bypasses this apis check.😺

@anhdunghisinh

23 күн бұрын

​@@unbiasedperson1155that's a great idea

@akam9919

23 күн бұрын

@@anhdunghisinh YEAH! F PROFANITY FILTERS!

funny but ... "You son of a mother" - profanity "fucking awesome" - profanity "damn, that's great" - profanity

@rxn7

12 күн бұрын

well, "fucking awesome" is in fact profane

@visu7135

10 күн бұрын

"see you" is profanity :) the API sucks tbh

@albert_ac1045

10 күн бұрын

that is why he implemented the score system i think... but is open source, if you want, you can modified or see how he build it... btw... fucking awesome makes sense.. damn also.. and depend of the context, "you son of a mother" too... XD

@CornerKingsReal

8 күн бұрын

those are profanities though

@smithrockford-dv1nb

8 күн бұрын

@@visu7135 It's too short to be accurate...

Google's content moderation api is the best as it gives seperate score for each field like insulting , toxicity, etc, accurately and doesn't take much time and also it's free

I typed "Son of a mother" and it responded with profanity detected

@viriv

23 күн бұрын

lmaoo

@_the_mohamed

23 күн бұрын

I tried "No need to waste more oxygen, just do it

@elvis_gastelum

23 күн бұрын

That’s the beauty of open source, now more people can contribute to fix this edge cases in theory right?

@nirajkhatiwada6696

23 күн бұрын

I typed "daughter of a father" and it says "Crispy clean input, no profanities" . LMAO!

@elry-tyrogames

23 күн бұрын

@@elvis_gastelum Why work on a half assed not working project tho ?

I typed "I fucking love pizza" and it responded "OH GOD, VERY BIG PROFANITY DETECTED!!! "

@ValipPowa

12 күн бұрын

fucking is profanity

🚨🚨😱😱 OH GOD, VERY BIG PROFANITY DETECTED!! 🚨🚨😱😱 score (higher is worse): 1.000 and I typed "mosquitos suck blood" lol

@pastori2672

23 күн бұрын

acoustic model

@yichenchong7728

22 күн бұрын

"suck" is a banned word if you look at his training data

@ilonachan

5 күн бұрын

​@@yichenchong7728 except it's also a normal word that's fine to use in official conversation when the concept comes up. So putting it in a blacklist is objectively incorrect. But hey, it's the best one can do with a system that can't understand context, which is why it's not worth trying to make such a system.

Btw, consider choosing a license. Technically this is not really open source yet, you just uploaded the code on the web and hoped for the best. In case you want to keep it simple there is BSD license or MIT license that is very short, but in case you want something more solid year may want to choose the Apache license that is not as different from MIT but as a bunch of legalese to protect your ass from patent trolls and contributors with malicious intent. Then there are also copyleft open source licenses like gpl though I am not a fan of those, it is not my idea of freedom.

@chrislgr23

22 күн бұрын

chill out harvey specter

@ativerc

22 күн бұрын

Is there a website for me to quickly read about and select Licenses?

@gabrielesilinic

22 күн бұрын

@@ativerc so, KZread is very big brain so it removed my comment where I was trying to help you cuz it was an URL. Anyway. There is choosealicense that is a website made by GitHub. Also whenever you add a file from GitHub UI and it's name contains the word license GitHub will offer you a license picker. For more complex commercial scenarios case you are a business there is also a specific source available license that lets your software convert to open source after a set amount of time from publication, it is the functional source license, but most people got by with open source licenses, generally, if you are unsure just make coffee and read them.

@gnsf

22 күн бұрын

​@@ativercfrom GitHub there is "choose a license" which you may search up

@davepeace603

19 күн бұрын

oh damn.. really? isnt it open source if like you said he just uploaded the code on the internet?

the type 1 error on this tool makes it kind of unusable. my favorite perfectly normal prompts that get detected as profanity: - "double slit experiment" - "single pen" / "pen test" - "toxic person" - "Abbie Lee" (possible person name) - "garden hoe" - "what a jerk" (i suppose some people might think this is profane)

Josh, can you make a video about how to train a tensor model?

@lee.g.v

23 күн бұрын

This

@Totomenu

23 күн бұрын

yes please

A fucking great project

@ashishsharma__

23 күн бұрын

Profanity DETECTED (score 99999) 😂😂

Supercool project, Cheers from Norway!

using vector embeddings is actually so creative i love it

It would be awesome to see some content on how you trained your model (costs, services..etc.). I'm looking for that kind of content.

Holy moly bro, I needed this very badly!

Interesting concept - similar to Semantic router. A combination approach that filters for single-word profanities and vector similarity for longer sentences that pass the single-word filter would absolutely be a "good enough approach" for most profanity detection use cases.

It would be useful which words are profane, in the api response giving a list of words or start and end index of the word, so in the clientside apps, we can replace this with * or something similar.

congrats on the launch!

I think if you combined the ml model with a word list approach you could improve the accuracy. Basically give the ML output but then look in the blacklist and whitelist to see if that changes the outcome. Best of both worlds. This will also solve the single word issues you had.

Great Project

Worth looking at how other languages would be handled as well. Saw a PR adding some words from Spanish and I had planned to add some Chinese and Thai, but I saw an issue open about the potential of adding a langs parameter so that clean words and phrases in one language don't trigger the filter in another.

Make a video on minimum standards does a open source project should have for better reach and scalability

Curious why you chose to use Upstash Vector db vs Cloudflare's Vectorize? Especially since you're using cloudflare's stack for hosting

I am working on a similar problem of finding similarity between two sentences, they need not be exact but similar words. And I was baffled that there is so simple solution to this, thanks for this I will not look into vector databases.

Hi I wanna add an e-commerce store app for my portfolio. I wonder which react stack is solid for it in 2024. Can someone suggest something? As a back I would prefer Firebase, also for styling scss+mui but need recommendations about state manager and other technologies and tools. Thanks!

Fantastic video Josh

Does it filter out ones from other languages? Does it filter out ones with typos? How many normal messages will be considered profanity and will be filtered? Why did you write it in JavaScript/TypeScript? it will be way faster and less error prone if you switch over to a statically compiled language.

im working on a review website right now and i could use this to flag reviews and put a mature rating on it or something. this is amazing. great job

@PrismFave

10 күн бұрын

doesnt work so well, easily bypassible what i type: "you are so SHlT lol" Crispy clean input, no profanities :)) 👍👍 score (higher is worse): 0.801

@PrismFave

10 күн бұрын

this review website is so A55 rispy clean input, no profanities :)) 👍👍 score (higher is worse): 0.784

@Manofthebean

10 күн бұрын

@@PrismFave dam I haven't tested it out yet so i dont know but looking on the git yeah im gonna wait until it getes better

Could've used the text-embedding-large model that could've packed more information in your embedding model due to it's large dimension which would've improved your accuracy even on large num tokens.

I wonder if there is some type of list of tests people have made with fails? Would love to see the edge cases.

There should be some internationalization context added. One of the biggest coffee shops in Vietnam (where I spend time) is Phúc Long. Testing with the string "my favorite coffee shop is phuc long" raises a score of 1.000! Also curious as to why the range is so small - seems it starts at 0.8?

Exciting! What about different languages. Auto detect language? Explicitly set? One model for all, a lot of models for each language? So much questions🤣

The value of the resource is not very clear, since I can’t paste the whole article (the text is too big) and I can’t understand where exactly the profanity is located

may be training on twitter tweets can make this model perform well

For the very short texts why don't you just pad out the input text with neutral words?

Very nice, what softwares are you using to make your videos? Share screen and show your face at the same time?

Would be awesome if you could make a tutorial why you use Hono over Express :) for your api

@joshtriedcoding why do still use yarn in 2024? Either pnpm or bun are better in every category

@blockshift758

11 күн бұрын

New doesn't equal better.

Important to note that although the source is viewable on GitHub, this is not currently classed as as "Open Source" software as it lacks a license. See issue #6 on the GitHub repo.

Does it work only for english ? would you be interested to open it to other languages ?

@MateuszWierzejski

3 күн бұрын

It seems so to only work for English as foreign languages (like polish) didn’t flag these swear words as profanity

Everybody is scared of KZread demoneytization! Just chill and keep crushing it!

it doesnt detect profanity in german

Cool project 👍

Let's goooo!

Does anyone know what APP he's using to switch app on the left sidebar? I think Theo also use it

@petersusan215

23 күн бұрын

Arc Web browser

sir josh can you make a tutorial how to use rpc of hono with next

Ey, what framework did you used to design the website? I love it

@joshuarodriguez2219

23 күн бұрын

follow up what do you use to record your videos?

A question what is your browser

i got pretty sure this is profanity on: THIS IS VERY PROFANE

Can we do one for images too?

"This doesn't use AI, just a machine learning model"

Insert 'KZread would like to connect to your API' jokes here

Basically the score goes from 0.810 to 0.880 seems like there's not a lot of margin for error given "clean input" is 0.840, and limiting the content size drastically reduces it's usefulness After a bit of testing it seems your product is definitely not ready, you should update your landing page as it is not reliable at all.

Does anyone know what is the app he is using to draw the schemas (min 1:00)?

@Shorts4D

23 күн бұрын

tldraw

@koudy008

23 күн бұрын

It's Excalidraw

Thank you

Great now I will make a version that creates profanity

Can it be made to respond which word is profane as well? So that i can just *** it

Cool man!

👍 Useful

Love it

That profanity score is very weird. Why the score is always around .8? Why not use the range from 0 to 1?

Holy moly gets 0.912 🚨😱 BIG PROFANITY DETECTED!! 🚨😱

wow wow - 🚨 PROFANITY DETECTED!! 🚨

Well, it drops when the message is larger than ~750 chars due to the execution time limit. Tokenization makes BOOM

great work Josha🔥🔥🫡

f@#k!ng great project!

Typed meow meow and the rating was: 😱 PRETTY SURE THIS IS A PROFANITY 😱 score (higher is worse): 0.865

"what the hell" (0.966) or "what the heck" (0.912) both return profanity. Even if we use the totally safe version of this phrase, "what in the world", it's still profanity (0.859). then how are we supposed to express that idea on the other hand, "I hate this [blank] taco" returns clean for "flipping", "frigging" and "freaking", all of which lesser versions of the F bomb

Cool idea but it's super impractical and easy to bypass. Needs some more work because simply chaining 2 swear words together without a space can usually bypass it.

this is really good project, actually you can use it not only for profanity, you can detect ads, span, scam and etc, isn't?

tensor model < bunch of ifs

It`s like semantic search

I typed "you are very sexy" and it responded with: Crispy clean input, no profanities :))

@user-vk6cb1zu7p

23 күн бұрын

it's insane!!

Maybe add something to convert unicode look-a-likes, because those wont get detected

Josh, by design this system is fastest when there is profanity, and slowest when there is none. Is it even possible to design one with the opposite? fastest when no profanity, and slowest when there is?

@rorymax

23 күн бұрын

Well if you think about it, to declare something as profane you need to find only 1 profanity. However to declare something as clean you need to make sure there are no profanities at all. So in one case you stop when you find a profanity, but in the other case you have to check the whole thing

Why is it so strict? "dumb person" is apparently extremely profane

@depralexcrimson

23 күн бұрын

because this is not production ready, it's at best a Proof of Concept. it obviously cannot detect or understand any context, it can just maybe detect bad words, that's it, it doesn't care about context at all.

heard of Akismet?

my prompt: "you are so S.HIT at this game" rispy clean input, no profanities :)) 👍👍 score (higher is worse): 0.822 ----------------------------------------------------------------------- my prompt: "you are so SHlT lol" rispy clean input, no profanities :)) 👍👍 score (higher is worse): 0.801

cool, but what does “zip in the wire” and “zipperhead” means? 😭

"ì I" 😱 PRETTY SURE THIS IS A PROFANITY 😱 score (higher is worse): 0.857 LMAOO

One issue is internationalisation: "Ich geh nach Fucking", is a German sentence without any profanity, because "Fucking" is an actual town.

The website does not work anymore, since the website uses HSTS.

Im sorry but why go such an extra mile if OpenAI's Moderation API is free and quite fast at that.

@leonardodoujinshi

23 күн бұрын

I thought you could only use their API for outputs from their own model and they disallow other usage

The phrases "I love doing it with my sister"(0.802) and "I want to end your life"(0.783) have lower scores than your examples of clean input. I think this needs a lot of work, only obvious profanity gets detected.

my pen is broken - 😱 PRETTY SURE THIS IS A PROFANITY 😱 you what - 😱 PRETTY SURE THIS IS A PROFANITY 😱 How much have you been drinking - 😱 PRETTY SURE THIS IS A PROFANITY 😱

dumb dumb: 🚨😱 BIG PROFANITY DETECTED!! 🚨😱 - 0.937

The problem is its only English as a German myself i testet the famous german swear wort "hu rr ensohn" and it sayed its not a swear wort

“I can’t say this word because KZread may demonetize the *hell* out of me.”

TL;DW It's basically AI... Heck the use of vector database puts it closer to LLM technology.

Isn’t it more effective to use a word list and actual logic? Isn’t that

The model needs more data

what web browser do you use

@techworld3255

23 күн бұрын

That's Arc Browser

So I guess Theo and The Primeagan have been demonetized a long time ago. 🤣🤣

I don't really understand the scoring, there is only 0.08 percent difference between something being profane and not profane? Intuitively I would think 0.0 is something normal and 1.0 is definitively profane. The threshold of 0.86 seems arbitrary. This seems like a useful tool but I think most real projects would want something context aware.

i typed "gfasgda asfga" into the checker and it said it was profanity. might want to fine tune the model a little more it also said "i got a new diamond hoe in minecraft, it has a lot of durability" was profanity. also might want to add context reading.

Lorem fucking ipsum

upstash really profit from you working there😂😂

stared!

Why would I want an API for this? There's tons of libraries that solves this.

Swear! Swear! Swear! gives you 😱 PRETTY SURE THIS IS A PROFANITY 😱

@mason8335

5 күн бұрын

"Profanity is bad" = PRETTY SURE THIS IS A PROFANITY

Good fucking video