Reduce Risks when Coding with AI, AI Consulting Opportunities, Mistral 7B Deep Dive #27

Author(s): Towards AI Editorial Team

Originally published on Towards AI.

Master the art of building LLMs with our 470+ page guide!

Good morning, AI enthusiasts! The last couple of weeks have been super busy with some really interesting launches, like our book and the b2b consulting services. But that’s not all; it has also opened up fun opportunities for you all. Find those in the collaboration section, along with other deep-dive articles, new apps, and more!

What’s AI Weekly

This week in What’s AI, I dive into a very important topic: the hidden dangers of AI in coding. If you are coding with ChatGPT or Copilot, you may be creating some terrible security leaks! A recent Stanford study found that in 4 out of 5 tasks, participants assisted by AI wrote less secure code than those without AI. I will focus on how to avoid those threats while still profiting from the gains of using generative AI when coding. Watch the video here or read the complete article here!

— Louis-François Bouchard, Towards AI Co-Founder & CTO

Learn AI Together Community section!

Featured Community post from the Discord

Battlescar_za has created a fun face-swap web app called Video Meme Machine. Created by meme lovers who wanted to dive into face-swap tech. They have built their own engine for doing this. Try it out here and support a fellow community member. Share your thoughts in the Discord thread!

AI poll of the week!

The nature of polls has been different lately, but it’s only to make sure we can create more of what you want from us. Head to the Discord thread and share everything you would like to learn.

Collaboration Opportunities

The Learn AI Together Discord community is flooding with collaboration opportunities. If you are excited to dive into applied AI, want a study partner, or even want to find a partner for your passion project, join the collaboration channel! Keep an eye on this section, too — we share cool opportunities every week!

1. At Towards AI, we have launched our business-to-business products to help teams adopt AI and bring the latest capabilities into their organizations. We will primarily focus on two fronts: customized corporate AI courses and consulting. If you think you can help us with teaching & consulting, reach out to [email protected]!

2. We are also looking for an AI technical writer and developer for large language models. If you can communicate complex AI concepts and methodologies to a broad audience, connect with [email protected], too!

3. Rais24452 is looking for fellow learners, beginners to experienced, to start learning AI & ML concepts and potentially create a group. If you prefer learning together, connect in the thread!

Meme of the week!

Meme shared by hitoriarchie

TAI Curated section

Article of the week

Breaking Down Mistral 7B ⚡🍨 by JAIGANESAN

This article explores the Mistral architecture, exploring its unique features and how it differs from other open-source large language models (LLMs). It focuses on concepts such as Rotary Positional Encoding, Sliding Window Attention, Grouped Query Attention, Feed Forward, Network in Mistral 7B, SiLU Activation Function, KV Cache and KV Cache with Rolling Buffer cache, linear layer, and softmax activation.

Our must-read articles

1. How Do Diffusion Models Work? Simple Explanation: No Mathematical Jargon, Promised! by Suhaib Arshad

This article breaks down the diffusion models that have already replaced State-of-the-art generative frameworks like GANs or VAEs. Diffusion models showcase the following capabilities: outperforming GANs in terms of high-quality and high-fidelity image samples, having a stable training process compared to GANs, and capitalizing on the probabilistic framework similar to VAEs, ensuring a structured latent space.

2. How Do Face Filters Work? by Vincent Vandenbussche

Everyone knows Snapchat filters. Face filters are everywhere now in our apps: Instagram, TikTok, Snapchat. But how does that even work? In this post, we’ll provide a short introduction and fully working Python code to allow you to create your own filter.

3. The Magic of Variational Autoencoders (VAE), Where Creativity Begins! 🎨

This article dives into the world of Variational Autoencoder (VAE) and explores what sets them apart from traditional autoencoder. This blog solely focuses on the reparameterization trick and the loss function that makes VAE different from the autoencoder.

If you are interested in publishing with Towards AI, check our guidelines and sign up. We will publish your work to our network if it meets our editorial policies and standards.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI