I’m excited to announce Fello AI version 4.4.0, with macOS 15.0 Sequoia optimization, faster response times, and improved model performance. On top of that, you’ll also find two new flagship models: Perplexity Online and Mistral Large 2. Let’s take a look at what’s new one by one:
Introducing Perplexity Online: AI, Always Up to Date
One of the key highlights in this release is Perplexity Online, a model designed to provide real-time, constantly updated information.
But what exactly is “perplexity” in AI?
Perplexity measures how well a language model predicts the next word in a sequence. The lower the perplexity, the better the model predicts, ensuring fluid, human-like conversations.
Key Features of Perplexity Online:
- Real-Time Accuracy: Unlike static models, Perplexity Online is connected to live data sources, constantly updating to reflect the latest facts and trends.
- Built on Llama 3.1: Powered by the highly efficient Llama 3.1 framework, it delivers accurate, up-to-date responses across a wide range of topics.
- Ideal for Knowledge-Intensive Queries: From current events to in-depth research, Perplexity Online keeps your answers relevant and timely.
Mistral Large 2: Power Meets Precision
We’ve also added Mistral Large 2, a flagship model built for handling complex queries with precision and speed.
Why Choose Mistral Large 2?
- State-of-the-Art Performance: Mistral Large 2 efficiently manages large datasets, delivering sophisticated outputs without slowing down.
- Versatility: Perfect for in-depth analysis, problem-solving, and creative tasks, Mistral Large 2 adapts to both technical and creative use cases.
- Energy Efficiency: Despite its power, Mistral Large 2 is optimized to use fewer resources, making it a perfect fit for macOS 15.0 Sequoia’s energy-efficient design.
Other Updates
Optimized for macOS 15.0 Sequoia
Fello AI has been optimized to work flawlessly under the latest macOS release Sequoia. Both performance and design-wise. Expect faster load times, seamless multitasking, and a more responsive UI that fully integrates with Sequoia’s enhanced resource management.
Faster Responses Across the Board
I’ve reduced latency for GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet. You’ll notice quicker replies, whether you’re solving problems or just having casual conversations.