Storytell Architecture Updates and Developments in Browser-Based Machine Learning
Storytell's new architecture, data model and in-browser LLM experiment
Why managing AI risk presents new challenges
Aliquet morbi justo auctor cursus auctor aliquam. Neque elit blandit et quis tortor vel ut lectus morbi. Amet mus nunc rhoncus sit sagittis pellentesque eleifend lobortis commodo vestibulum hendrerit proin varius lorem ultrices quam velit sed consequat duis. Lectus condimentum maecenas adipiscing massa neque erat porttitor in adipiscing aliquam auctor aliquam eu phasellus egestas lectus hendrerit sit malesuada tincidunt quisque volutpat aliquet vitae lorem odio feugiat lectus sem purus.
- Lorem ipsum dolor sit amet consectetur lobortis pellentesque sit ullamcorpe.
- Mauris aliquet faucibus iaculis vitae ullamco consectetur praesent luctus.
- Posuere enim mi pharetra neque proin condimentum maecenas adipiscing.
- Posuere enim mi pharetra neque proin nibh dolor amet vitae feugiat.
The difficult of using AI to improve risk management
Viverra mi ut nulla eu mattis in purus. Habitant donec mauris id consectetur. Tempus consequat ornare dui tortor feugiat cursus. Pellentesque massa molestie phasellus enim lobortis pellentesque sit ullamcorper purus. Elementum ante nunc quam pulvinar. Volutpat nibh dolor amet vitae feugiat varius augue justo elit. Vitae amet curabitur in sagittis arcu montes tortor. In enim pulvinar pharetra sagittis fermentum. Ultricies non eu faucibus praesent tristique dolor tellus bibendum. Cursus bibendum nunc enim.
How to bring AI into managing risk
Mattis quisque amet pharetra nisl congue nulla orci. Nibh commodo maecenas adipiscing adipiscing. Blandit ut odio urna arcu quam eleifend donec neque. Augue nisl arcu malesuada interdum risus lectus sed. Pulvinar aliquam morbi arcu commodo. Accumsan elementum elit vitae pellentesque sit. Nibh elementum morbi feugiat amet aliquet. Ultrices duis lobortis mauris nibh pellentesque mattis est maecenas. Tellus pellentesque vivamus massa purus arcu sagittis. Viverra consectetur praesent luctus faucibus phasellus integer fermentum mattis donec.
Pros and cons of using AI to manage risks
Commodo velit viverra neque aliquet tincidunt feugiat. Amet proin cras pharetra mauris leo. In vitae mattis sit fermentum. Maecenas nullam egestas lorem tincidunt eleifend est felis tincidunt. Etiam dictum consectetur blandit tortor vitae. Eget integer tortor in mattis velit ante purus ante.
- Vestibulum faucibus semper vitae imperdiet at eget sed diam ullamcorper vulputate.
- Quam mi proin libero morbi viverra ultrices odio sem felis mattis etiam faucibus morbi.
- Tincidunt ac eu aliquet turpis amet morbi at hendrerit donec pharetra tellus vel nec.
- Sollicitudin egestas sit bibendum malesuada pulvinar sit aliquet turpis lacus ultricies.
“Lacus donec arcu amet diam vestibulum nunc nulla malesuada velit curabitur mauris tempus nunc curabitur dignig pharetra metus consequat.”
Benefits and opportunities for risk managers applying AI
Commodo velit viverra neque aliquet tincidunt feugiat. Amet proin cras pharetra mauris leo. In vitae mattis sit fermentum. Maecenas nullam egestas lorem tincidunt eleifend est felis tincidunt. Etiam dictum consectetur blandit tortor vitae. Eget integer tortor in mattis velit ante purus ante.
Hi, users! The engineering team has been hard at work at making improvements on how Storytell works. We're excited to share some of these updates with you and provide a glimpse into the future of our platform:
- Architecture and Data Model Updates
- Overview:
- The control plane (the "brain" of the system) coordinates various tasks such as content ingestion, machine learning services, and user interactions. We're continuously improving the architecture to provide a seamless user experience.
- The model plane will have a multi-model planner that breaks down user intents into multiple tasks for efficient and targeted content generation. An LLM router will choose the best model based on the task, ensuring optimal performance and cost-effectiveness.
- Data model improvements
- We're implementing a user aggregate system that tracks user events (e.g., account creation, email verification) as a linear timeline. This allows for better auditing, data integrity, and the ability to reinterpret events without complex data migrations.
- Every operation in the system will be represented and tracked, allowing for cost accumulation and transparency. This will enable us to optimize performance, analyze user behavior, and potentially offer flexible pricing models in the future.
- Running Machine Learning Models in the Browser
- Proof of concept: We successfully ran BERT, a text-classifying model, directly in the browser. This groundbreaking development opens up a world of possibilities for enhancing the user experience and reducing latency.
- Implications for user experience: By running models in the browser, we can provide near-instant results, enabling features like auto-complete suggestions and real-time model selection based on user input. Imagine typing and receiving immediate, context-aware suggestions powered by machine learning models running right in your browser!
- Cost-saving benefits: Offloading computations and processing to the user's browser reduces the load on our systems, potentially leading to cost savings that we can pass on to our users
.png)
.png)