Using Janitor AI is really simple – just create an account and start chatting with the characters. And if you don’t like the Language Learning Model (LLM) you’re interacting with, you can change it using APIs.
By default, you get to interact with JanitorLLM Beta. It’s in beta so you can expect strange behavior and some downtime.
To reduce the downtime and have refined results, you can use OpenAI or Kobold AI running in the background.
If you haven’t tried Character AI yet, you’ve been missing out on a whole chunk of AI fun. It doesn’t feel like chatting with bots at all – at least with some characters.
Try chatting with a few of the most popular characters and you won’t know where your day went.
Continue reading “6 Best Character AI Alternatives for 2024 (Updated Monthly!)”
In [a previous tutorial], the Levenshtein distance was used in an Android app to suggest words as a user types to automatically complete the word and save time.
In this follow-up tutorial, the suggestions will be enhanced by comparing the text the user is typing to words that are likely to be a match. Moreover, the app will support early exit if the distance exceeds a pre-defined threshold, which helps save time and enhance the suggestions.
Continue reading “Enhancing Word Suggestions for Auto-completing Text in Android”
Document processing is one of the most time- and resource-consuming tasks, compared to the value added that comes from the output.
It takes hours of manual, diligent work to input data in invoices, update medical records, or create the folders for insurance claims.
If all of these tasks could be done automatically, we’d see important benefits, including better organization of the underlying data, automatic scanning of records, error-checking, and pattern detection.
Continue reading “Why AI Is the Next Step in Document Processing”
For a moment, travel back in time with me to 2011. Back then, Kotlin was a garage project by a team at JetBrains and had already been under development for a year. The team’s main goal was to have something that had all the goodness of Scala but still compiled as fast as Java. They open-sourced the project in early 2012 under the Apache 2 License.
Continue reading An Introduction to Kotlin on Android — Concision and Safety
Is your model not performing well? Try digging into your data. Instead of getting marginal improvements in performance by searching for state-of-the-art models, you can drastically improve your model’s accuracy by improving the quality of your data.
I’ll be honest with you—I’m horrible at all things art. I was the kid who had to stay after class in 7th grade art because I could not, for the life of me, figure out shading. After years of half-hearted, failed attempts at scratching something decent onto a sketch pad, I resigned myself to the fact that I just wasn’t meant to be an artist.
One of the things I find most fascinating about technology is the ways in which it can clear pathways I would’ve imagined blocked. I’ve found that to be true as I’ve learned more and more about machine learning and mobile development, certainly.
To use ChatGPT for free. Just open ChatGPT on your browser or download its app on your mobile phone. Just enter your question or requirement in the prompt box and click on the Send button. You’ll get your answer in just a second.
Continue reading “How to Use ChatGPT for Free (With Examples)”
Of all the tools I tested for AI voice generation, ElevenLabs was the best for instant voice cloning. It lets you choose any style, accent, and voice and also offers text-to-speech options.
It supports 29 languages and after testing almost 10 other AI voice generators including Speechify and Amazon Polly, I think ElevenLabs provides the best stability and clarity.
Continue reading “The Most Detailed ElevenLabs Review 2024 (Plus Competitor Analysis)”
On my not-too-shabby laptop CPU, I can run most common CNN models in (at most) 10–100 milliseconds with libraries like TensorFlow.
In 2019, even a smartphone can run “heavy” CNN models (like ResNet) in less than half a second. So imagine my surprise when I timed my own simple implementation of a convolution layer and found that it took over 2 seconds for a single layer!
It’s no surprise that modern deep learning libraries have production-level, highly-optimized implementations of most operations.
Continue reading “Anatomy of a High-Performance Convolution”
