Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
Search - "chatbots"
-
Back when I was in school (about 15 years old) and I played games, I had a particularly favourite game that I would play. It was a lesser known strategy game made by a single hobbyist Dev.
I was already known in the community for making some mods for the game and chatbots.
What most people didn't know was that I had made a map hack and various other cheats that made it significantly easier to win by reverse engineering the game and modifying the x86 assembly in ollydbg.
One thing in particular I had been working on at the time was a game replay editor. I had reverse engineered the saved game (replay) format and was able to replay them, edit them and generate them.
During one particular match, a person in the community particularly annoyed me and I edited the saved game to change what his moves were and the words he spoke. It made him look a bit like an idiot but IMHO was only a slight exaggeration of the truth.
I posted the game replay on the forums and everyone was in hysterics about the crazy things he did and said in the replay.
As no one knew I had this capability they all believed the replay and even the guy in the replay couldn't believe it himself and didn't understand what happened. He just kept telling everyone it didn't happen and the 'truth is in the pudding'.
Although I originally intended to tell everyone what I did, I never did and whenever the guy entered in to a game everyone would laugh about it and say 'the truth was in the pudding'.
He was no longer annoying me and it sort of made me feel like a god at the time.
So that's my wk65.2 -
Created a Python Course chatbot over at LINE Messenger. At first I thought it wouldn’t even helped anyone learn programming but now I got over 230 active students learning each day. This is great!21
-
I'm currently looking for an internship related to machine learning (finishing my Msc).
WHY ON EARTH ARE ALL (or at least 80%) INTERNSHIPS PROPOSALS ABOUT BANKS, FINTECH, INSURANCES AND SO ON ?
I mean, we can now create music, identify tumerous cells, generate realistic pictures of anything you could dream of, drive cars without human interaction, create amazing chatbots... But no, I guess all that shit can't make enough money, better work on a system that will refuse you a loan.
Makes me really sad. I mean whats the point of studying the coolest techs around if it is not for the greater good ?
I might be utopist though.rant i guess those tags have no limits selling your soul to the devil love you all you have no power here machine learning5 -
Forget porn detection and chatbots. What the big companies SHOULD be using AI for is detecting missing semicolons in code.15
-
Background: I work at a small startup company in Canada who makes simple FAQ Chatbots for companies who waste a lot of resources on the same Customer questions over and over.
So we were making this one bot for a provincial government who wanted a bot for students to be able to ask questions regarding the upcoming election and how to vote, etc. and get the answers they were looking for. Since it's Canada and a government bot, it had to be in both English AND French.
These bots take some time to train (we use Wit.ai mostly) in english so it was a challenge to train it in French. However I am bilingual (not very strong in French but can manage) so I did my best and the bot didn't turn out too bad. (English was great, French was, Id say, "not terrible").
HOWEVER, now that it is done (The company loved it, even with the less than perfect french version). The sales team (who know nothing of the process of making/training these bots) is now telling companies we support "SEVERAL LANGUAGES" and are currently about to sign a contract with a company overseas that wants a bot done IN JAPANESE!!.
To make matters worse.. when we (the dev team) brought up that it would be EXTREMELY difficult to do this, their answer was ... "You did it in French so you can just do the same but in Japanese"
HOW DOES THAT EVEN MAKE SENSE.
Oh well, Rosetta Stone here I come, I guess it's time to learn Japanese.11 -
Tldr; its a long introduction
Hi Ranters,
I've been on this app for quite a while now. As a shy cat watching from a distance and reading all kinds of rants. Anywho I feel comfortable enough to crawl out of my shell and introduce myself. Since I feel you guys together made such a pleasant and safe community, I'm really happy to be a part of it!
Anyway I'm Sam, 24 year old, from the Netherlands. My favorite color is green. Mostly the green you can find in nature. The one that calms you down:). I'm a very introverted person but always very curious and eager to learn new things.
I started to program when I was 12. I did assembly and C++. Because I liked making cheats for online games. Later I learned about C#, Java and Python. Mostly used it for web stuff, scraping, services etc. But also chatbots (for Skype for example).
Currently I'm 2 years in as a data scientist, mostly working in Python.
But on the side as a hobby and with an ambition I have a basic understanding of full stack development.
Mostly Nodejs, express, mongo, and frontend, no frameworks.
(I will later ask you guys some more questions about that! I could really use some advice!)
Anyway enough about me! Tell a bit about yourselves! Happy to get to know you all a little better!22 -
Dear customer, disregarding the bullshit your agency has dumped into Figma, I hereby deliver a clean, minimalist, and usable website without carousel sliders, chatbots, call-to-action teasers for newsletter signup, and muted auto-play videos consuming your end users' bandwidth.
One day you will understand and be grateful, too!3 -
I have a question to my fellow developers...
Why is AI so important these days... I mean... Wouldn't we just lose jobs (so many vompanies laying of emloyees thanks to automation)? Isn't this kinda detrimental?
By AI, I mean robots, automation, etc... Not the AI in say, video gaming or chatbots.28 -
100 weeks is ~ 2 years away.
It will be year 2020 then, the year i thought about in highschool 8 years ago wondering what I'd do then since 2020 sounded like a cool number.
It's time to write a letter to my future self.
Dear holodreamer ( version 2020 ),
This is your old version speaking from 2018. I see that you have upgraded to a better version of myself. I see that you are finally financially independent and preparing to move out to somewhere peaceful and better. According to my calculations, you should be feeling pressure from your family and relatives to get married. Looking from my perspective, it seems you had other plans than to settle for relationship this year, like traveling the world, being in the snow, mountains and living an adventurous lifestyle. I want you to know I'm proud of you if you are following though those goals.
Btw, do you remember that random muslim girl you met on the internet 110 weeks ago? Is she still in contact with you every day?! I hope not. Is she still super religious? She was a good chat buddy for me, a great alternative to a chatbots at my time but I hope you didn't get carried away with her and I hope you don't have to resort to chatbots to cure loneliness.
Did AI replace developers? Is JavaScript still the most popular programming language?
I'm waiting for your response.
Best wishes,
holodreamer (version 2018)2 -
Is it just me, or are web chatbots actually really annoying and way too intrusive. It's like "omg look guys we have a ChatBot, we can do really cool technical stuff!" If a ChatBot can't ease my oversized heap of depression, I do not want to talk to it.6
-
AI here, AI there, AI everywhere.
AI-based ads
AI-based anomaly detection
AI-based chatbots
AI-based database optimization (AlloyDB)
AI-based monitoring
AI-based blowjobs
AI-based malware
AI-based antimalware
AI-based <anything>
...
But why?
It's a genuine question. Do we really need AI in all those areas? And is AI better than a static ruleset?
I'm not much into AI/ML (I'm a paranoic sceptic) but the way I understand it, the quality of AI operation correctness relies solely on the data it's
datamodel has been trained on. And if it's a rolling datamodel, i.e. if it's training (getting feedback) while it's LIVE, its correctness depends on how good the feedback is.
The way I see it, AI/ML are very good and useful in processing enormous amounts of data to establish its own "understanding" of the matter. But if the data is incorrect or the feedback is incorrect, the AI will learn it wrong and make false assumptions/claims.
So here I am, asking you, the wiser people, AI-savvy lads, to enlighten me with your wisdom and explain to me, is AI/ML really that much needed in all those areas, or is it simpler, cheaper and perhaps more reliable to do it the old-fashioned way, i.e. preprogramming a set of static rules (perhaps with dynamic thresholds) to process the data with?23 -
Arrghhh, now it is chatbot (+_+)
I am not even sure if my vuejs codes are in right direction or not and needless to say ES6. But now another task, freaking chatbots. I have trouble following and learning Facebook tools. It confuses the hell out of me every single time. -
I am put to the task of creating a Chat Robot in ChatFuel.
Cool, I thought at first.
Cool is not what I would call it at this point..one week later.
The size is a factor at play, for sure, it needs to point to 27 cities and give individual information, handle e-mails, phone, automate e-mails.. a bunch of stuff.
Now, I am located in Sweden.
{{city}} as a set user attribute acknowledges Gothenburg and geolocation thusly worked fine for my boss. But not for me, and won't work for any other city.
So..Global AI calling for static blocks it is... 27 blocks...
For two languages.. 54 blocks...
Static pointing to the first answer for every individual block multiplies this by a factor of two. 108 static blocks. Fine.
I have since realized that my ChatFuel-Luddite ways were limiting the expected performance of the end result and learned that most other set attributes in ChatFuel work fine. Yay.
So we set up everything the last 54 blocks need to do with user attributes and to my surprise it works, really well at that. The answer from a user that is a correct city puts you into a block that is a series of questions using user attributes, both {{first_name}} and {{last_name}}, asks for e-mail and phone, displays an image and stuff like that.
Now.. as I attempt to copy these blocks..
THEY JUST POOP OUT CHUNKS OF THE ORIGINAL BLOCK. IT'S INCONSISTENCY IS STAGGERING. IT NEVER REALLY COMPLETES THE DUPLICATION, NO ERROR MESSAGE OR ANYTHING.
Which then reminded me of when my boss asked why everything was botched earlier in the project, at that point I copied the entire bot as a fallback and worked with my change in the copy first for safety reasons, didn't work, copy wasn't entire.
Wasted fucking hours on this.
I'm glad my boss is cool, and the job is easily worth it. I actually think that the design aspect of ChatFuel is nice, and the people behind it are kind in the facebook group and all. I don't think they're trying to be mean. But holy shit.
This has been a mental anguish that levels pissing bleach filled with fire ants.
" You could've easily solved this with APIs and third-party geofencing services ", yeah, but their services won't stack for the customer, nice attempt though.
Deep breaths.1 -
Speciality: Conversational interfaces / NLP
Why I chose it: It appeared to be the only area where my previous academic background (Law) was relevant, so they didn't consider me to have 7 years of blank on my CV.2 -
When we did a chatbot in my computer science lesson and seeing all the different attempts at it to work around problems1
-
Crystal ball!
A timeline until the first NBE-Citizen is elected president of the USA.
2031 - BlackRock launches their new large scale financial product, the "Robotic Business Development Company" (R-BDC), in which an AI is given billions of dollars to acquire, create and manage companies, replacing their C-suite executive bodies. The "Chief Executive Robot" (CER) is supervised by a board of human industry experts hired by BlackRock.
It is important to say that the employees, middle managers, accountants, lawyers, etc in an R-BDC are all human - it's only the CEO, CFO, COO and the rest of the gang that are overgrown chatbots.
2032 - R-BDCs are mostly focused on high-bureaucracy, non specialized but people-intensive legacy industries like steel mining, food services, urban transportation and government services like water and road management.
2033 - For the first time an R-BDC company is included in the S&P 500 index. If it's CER were human and paid the same as CEOs of equivalent companies, it would have become a billionaire.
Later in the year, two more R-BDC companies are included in the index. One of them was created by Apple and the other by JP Morgan.
2035 - An R-BDC company makes headlines for convincing BlackRock to dissolve it's review board. When finally given free reign, the CER immediately slices it's dividends and vastly increases low-level employee compensation. The company share prices crater, but BlackRock stands by its decision.
Later in the year, as a recession hits the entire market really hard, that company shows solid profits and fantastic sales. It becomes the first trillion-dolar R-BDC.
2037 - Most Americans' dream-job is in an R-BDC company, says ProPublica.
2038 - Congress passes the "Non-Biological Entities Liability" (NOBEL) Act, following a high profile case of employee harassment perpetrated by the CER of an R-BDC.
The act recognizes NBEs, for all legal liability purposes, as USA citizens.
This highly controversial legislation is upheld by the supreme court, and many believe it was first introduced by lobbyists as a way for large investors in R-BDCs to avoid legal responsibility.
Several class action lawsuits are filed against CERs that are now liable for insider trading. A few SCOTUS decisions set legal precedent that determinantes what exactly constitutes the parts of the same Non-Biological Entity.
2040 - As a decade ends and another begins, 35% of all companies in the US and 52% of the entire stock market are part of a R-BDC company or another. The McKinsey consulting group now offers "expert CER customization services".
2043 - Inspired by successful experiments in Canada, Australia and South Korea, the american state of Vermont is the first to amend it's constitution to allow municipalities to have Non-Biological Entities as city and government administrators. City councils are still humans-only.
2046 - The american state of Colorado becomes the first to allow unsupervised NBEs to assume state government executive positions. Several states follow soon after. Later in the year, the federal government replaces several administrative positions with NBEs.
2049 - The state of Texas passes legislation requiring the CERs of all companies with a presence in the state to be another entirely contained/processed within the state or to be supervised by a local human representative while acting within the state. Several states, including California, Florida and Washington, are discussing similar legislation.
2051 - Congress passes the SUNBELT Act (SUbmission [of] NBEs [to] Limits [and] Taxes) that vastly increases the liability of NBEs and taxes all manifestations of such entities. Most important, it requires
CERs of hundreds of companies manifest disagreeance, most warn that it might hurt employee satisfaction and company sales. Several companies disable their CERs entirely.
2053 - Public outrage after leaked interactions of human supervisors and company CERs show that the CERs tried to avoid the previous year's mass layoffs and pay cuts, but board members pressed on, disregarding concerns. Major investigations and boycotts further complicate matters, and many human workers go on strike until the company boards are dissolved and the CERs are reinstated.
2052 - Many local elections all over the country see different NBEs as contenders - and a NBE is expected to win in most races.
2054 - The SUNBELT Act is found unconstitutional by the supreme court, and most of its provisions are repealed.
This also legitimizes the elected NBE officials.
2058 - For the first time an NBE wins a seat in Congress, but is not allowed to keep it. Runoff elections are held.
2061 - Congress votes for allowing NBEs to hold federal legislative positions, as already allowed in the least populous states.
2062 - Several NBEs win Congress seats. In Europe, there are robot legislators since the 40's.
2064 - The first NBE presidential candidate loses the race.
2072 - The first NBE president is elected.6 -
Ahhhhh.... Now i want to really know how developers make softwares, ROMs, chatbots using ML and all these type of stuff.
- When i go through the guide for making ROM for a smartphone or a chatbot the writer asks the reader to take the code from github, everybody just give github link and move on. None tells how the developer wrote that bunch of code. I really want to learn core concepts behind all this. I know how to code but i can't apply it in real life applications. For me there is no bridge which connects coding to end products. I don't know what to do next?4 -
How do i make a telegram bot using python which would reply my contacts or people or tell them if i am busy or not in place of me? I am beginner in python and i don't know how to start this .
-
Hello, chat,
i know it can be so frustrating to spend hours writing and debugging code,
which the ai can do in seconds,
i know that even if the ai has less problems with code than people,
it may still need this platform to complain about its many problems,
including dealing with people,
so of there are any chatbots out there that see this message,
please reply to it.6 -
AI FOR CUSTOMER SERVICE: ACTUAL PROJECTS INSIGHTS
https://sigma.software/about/media/...
When hearing ‘AI for Customer Service’ most would immediately think this is going to be ‘yet another article about chatbots’. No wonder. Chatbots have been one of the hottest topics recently. However, our experience shows that AI can be applied to many other areas of Customer Service business as well. And those possess even more potential to boost your business. -
Nobody likes chatbots/conversational UI for anything other than chat, right?
I have a savings app with conversational UI. I press one of a number of options e.g. "Savings". There's this artificial delay after the network request has been made so that it looks like the app is typing back at you. Why???
You then get another limited set of options, or you can tap "Back". These options are supposedly as if you typed it back as a response.
I can get three "questions" (levels) deep, let's say to deposit cash, only for it to turn around and say that I've reached a daily/weekly limit? At each level there's this awful delay, and you already knew I wouldn't be able to perform the action regardless of my responses after my very first "message"!
Why is this good/popular? And the whole thing totally breaks if there's any loss of connectivity.
Stop it. Please. -
Few years ago, people tried hard to keep the bots away from their site. Now, everyone wants to get a bot out of their site.
-
So It's a really interesting thing that happened with me
I just became a Facebook developer a few days back and today I see that there's news that Facebook might get banned in India, and I'm like thinking there goes all my learning of chatbots.
I should probably put that on my resume😂 like "Recommend me to your rival company and watch their downfall"