Tips

December 28, 2023

5 mins

The AI Corner

Hello Niuralogists!

In the ever-evolving realm of artificial intelligence, this week's edition is committed to delivering the most recent breakthroughs. Our central focus is to analyze how these advancements impact different facets of our lives, including workplaces, businesses, policies, and personal experiences. In this issue, we will explore some updates such as Apple's Research Initiative delving into AI integration on iPhones and OpenAI's initiation of talks for a funding round aiming for a valuation surpassing $100 billion. 

For a deeper insight, continue reading...

Exploring AI Integration on iPhones: Apple's Research Initiative

Apple is delving into AI integration on iPhones, as evidenced by recent research publications unveiling transformative techniques for advanced AI functionalities on mobile devices. These innovations span virtual assistants to 3D avatars, promising significant improvements. Notably, one paper focuses on efficiently generating animated human avatars from iPhone videos, showcasing advancements in photorealism and speed. Another paper outlines optimizing bulky language models using flash storage, enabling the smooth operation of complex applications like chatbots on mobile devices. Despite Apple's historical caution in embracing AI publicly, the company has recently intensified AI hiring efforts, with reported plans to incorporate AI into wearables, particularly for health tracking. This forward-looking research suggests that while appearing to lag in the AI race, Apple is quietly gearing up for a substantial impact. The integration of advanced AI into the iPhone, when it happens, could mark a transformative moment in adoption and demand.

OpenAI Initiates Talks for Funding Round with a Target Valuation Exceeding $100 Billion

OpenAI is currently engaged in preliminary discussions to secure a new funding round, aiming for a valuation equal to or surpassing $100 billion, notwithstanding the ongoing tender offer at an $86 billion valuation. The potential success of this new deal would position the creator of ChatGPT as the second-most valuable startup in the United States, trailing only behind SpaceX. Concurrently, OpenAI has explored funding possibilities for a novel chip venture in collaboration with Abu Dhabi-based G42, as reported by Bloomberg. This development marks a notable turnaround for OpenAI, as recent uncertainties about its future have seemingly dissipated, coinciding with the return of Sam Altman and instigating renewed confidence among potential backers.

Source: Pexels

Bill Gates Unveils AI Forecasts for 2024

Bill Gates has shared his optimistic AI predictions for the year 2024 in a recent blog post, envisioning a substantial impact on healthcare, education, work, and overall innovation. Anticipating significant mainstream adoption of AI in advanced economies like the U.S. within the next 18-24 months, Gates highlighted ambitious medical AI projects addressing issues such as antibiotic resistance and high-risk pregnancies. He expressed optimism about AI's transformative role in personalized learning through individualized tutoring and commended innovations like localized chatbots tailoring educational content to specific student needs. Contrary to previous reservations, Gates now foresees AI augmenting roles and enhancing productivity on a broad scale, emphasizing its potential to boost rather than replace jobs. This shift in perspective offers a positive and transformative outlook for the imminent advancements in AI.

Microsoft Copilot Unveils Capability to Generate Complete AI-Generated Songs

Microsoft's Copilot has recently integrated the music creation app Suno into its conversational AI, allowing users to convert text prompts into fully realized AI-generated songs complete with lyrics, instruments, and vocals. Suno leverages Copilot's language expertise to synthesize songs based on provided text prompts. The feature is currently rolling out to Microsoft Edge users and is accessible through Copilot's plugins tab. While Suno claims that its models don't recognize artists by name and are designed to block specific prompts, users have reported receiving genre-matching requests. This collaboration comes amid fierce competition in the AI audio space, with Google/YouTube’s Lyria and Meta’s Audiobox gaining traction. This innovation marks a significant step in AI audio, raising questions about its implications for the traditional music industry amidst ongoing debates about AI's role in creative processes.

Newsletter

📬 Receive our amazing posts straight to your inbox. Get the latest news, company insights, and Niural updates.

Thank you! Your message has been received!
Oops! Something went wrong. Please fill in the required fields and try again.

Q&Ai

How to train a SD model for consistent characters?

Learn how to train a Stable Diffusion (SD) model for consistent characters with LensGo, a web-based AI app. Developed by Chase Lean, this tutorial guides users through the process of training custom models using their own photos to ensure coherence in AI-generated images. The step-by-step instructions include visiting LensGo, where users can train three custom models for free each month. By selecting "Train Custom Model" and uploading 10-20 images of themselves or a specific character, users can initiate the training process by clicking "Start." After allowing the app 20 minutes to train on the provided photos, users can return to input simple prompts, generating AI characters consistently across various settings.

How to run  AI assistants locally on your phone?

Explore the groundbreaking LLMFarm app, which offers the ability to run robust AI models directly on your iPhone or iPad offline, ensuring both accessibility and privacy. Follow Alvaro Cintas' tutorial for a smooth setup: begin by installing the app through the LLMFarm TestFlight page, utilizing the TestFlight app if not already installed. Complete the process by clicking "Start Testing" in the LLMFarm app. Choose a pre-trained AI model from HuggingFace, such as the Mistral-7B model, download it from the 'files and versions' tab, and note the potential storage requirements. Incorporate the model into LLMFarm by selecting "Add Model," locating the Mistral 7B file, and inputting <s>[INST] [INST] in the 'format' section. Enhance performance by enabling Metal and MLock in the prediction options. Alvaro Cintas' tutorial provides a comprehensive guide to unleash the power of AI assistants locally on your mobile device.

Tools

🎞️ HeyGen’s Personalized Video Generator  mass-produces tailored videos for your audience 

🎨 Magic Hour is an AI-driven app for creating videos, inspired by a forbidden passion for art 

🧬 Helix is a custom-build AI using open-source software and personal datasets 

🍔 Rex Nutribot is an AI-powered tracking for calories, workouts, and meals via WhatsApp 

🎨 Drawww is an iPad-optimized real-time AI drawing tool

📸 Picmojo upgrades your everyday images into professional headshots 

Follow us on Twitter and LinkedIn for more content on artificial intelligence, global payments, and compliance. Learn more about how Niural uses AI for global payments and team management to care for your company's most valuable resource: your people.

See you next week!

Request a demo