How "Not" to Add a Generative AI layer to Your Product

Aug 2023

7 Mon

8 Tue

9 Wed

10 Thu

11 Fri 09:00 AM – 06:00 PM IST

12 Sat

13 Sun

Make a submission

Accepting submissions till 04 Jul 2023, 12:30 PM

Bangalore International Centre (BIC), Bengaluru

Tickets

Pinned update

Session on "Use Cases and Risks of ML in Capital Markets" | 23rd Dec at 4pm Hi everyone! The AI and Risk Mitigation project is well underway and for the third session, we will be joined by Rachna Maheshwari, Associate Director at CRI… more

The Fifth Elephant 2023 Monsoon Edition event recap is now up here . The event was attended by 192 participants, of which one-fourth were women. The Fifth Elephant videos are available to watch here

Event highlights:

Editors

The 2023 Monsoon edition is curated by:

Nischal HP, Vice President of Data Engineering and Data Science at Scoutbee. Nischal curated the MLOps conference which was held online between 23 and 27 July 2021.
Sumod Mohan, Founder and CEO at AutoInfer. Sumod curated Anthill Inside 2019 edition, held in Bangalore on 23 November.

Tracks and themes

AI and Research - covers research, findings, and solutions for challenges on building models in various areas such as fraud detection, forecasting, and analytics. This track delves into the latest methodologies for handling challenges such as large-scale data processing, distributed computing, and optimizing model performance.
Industrial applications of ML - covers implementation of AI in the industry, with more focus on the AI models, the issues in training, gathering data so, and so forth. ML is being used at scale in industries such as automotive, mechanical, manufacturing, agriculture, and such domains. This track focuses on the challenges in this space, as we see innovation coming out of these industries in the pursuit of using ML on a second-to-second basis.
AI and Product - covers strategies for building AI products to scale and mitigating challenges. This track provides insights on incorporating AI tools and forecasting techniques to improve model training, developing a working model architecture, and using data in the business context.

There are three phases in the lifecycle of an application - research, application and aftermath of the application.

Assess capabilities, determining the new frontiers for AI.
Find a use for the application.
Learn how to run it, monitor it and update it with time.

The three tracks at the 2023 Monsoon edition of The Fifth Elephant will cover this lifecycle.

The Fifth Elephant 2023 Monsoon edition will be held in-person. Attendance is open to The Fifth Elephant members only. Pick a membership to attend the in-person conference. If you have questions about participation, post a comment here.

Who will benefit from participating in The Fifth Elephant community:

Data/MLOps engineers who want to learn about state-of-the-art tools and techniques, especially from domains such as automobile, agri-tech and mechanical industries.
Data scientists who want a deeper understanding of model deployment/governance.
Architects who are building ML workflows that scale.
Tech founders who are building products that require AI or ML.
Product managers, who want to learn about the process of building AI/ML products.
Directors, VPs and senior tech leadership who are building AI/ML teams.

Sponsorship

Sponsorship slots are open for:

Infrastructure (GPU, CPU and cloud providers) and developer productivity tool makers who want to evangelise their offering to developers and decision-makers.
Companies seeking tech branding among AI and ML developers.
Venture Capital (VC) firms and investors who want to scan the landscape of innovations and innovators in AI and who want to source leads for investment in the AI and ML space.

Contact information

Join the @fifthel Telegram group or follow @fifthel on Twitter. For any inquiries, call Hasgeek at +91 7676 33 2020.

Hosted by

The Fifth Elephant

All about data science and machine learning

Supported by

LlamaIndex

E2E Networks Limited

E2E Cloud is India's first AI hyper scaler, a cloud computing platform providing accelerated cloud-based solutions at maximum optimization and lowest pricing

All submissions

Previous Next

How "Not" to Add a Generative AI layer to Your Product

Submitted Jun 28, 2023

Abstract

Artificial Intelligence, particularly generative models, are driving unprecedented transformations in products and services across industries. However, integrating generative AI is not just a matter of “plugging in” the technology.

In this talk, we will delve into the practical challenges and best practices of effectively incorporating these models into your product in a reliable and efficient way. We will focus on applications including text to SQL/JavaScript, text summarization, and retrieving relevant results from documentation, ensuring the outputs are accurate, domain-specific, secure, and performant. We will address the importance of avoiding hallucinations and handling prompt hacking/injection attacks in a real-world context.
(This is talk is based on my personal experience of implementing Generative AI layers into existing products)

Key Points:

Introduction to Generative AI: Briefly explain generative AI models like LLMs (Language Learning Models), their strengths, weaknesses, and potential applications.
Common Implementations:
- Text to SQL/JavaScript: Generate insghts, analytic or code using only Natural language conversations.
- Text Summarization: Get the gist of long 100 pager documents in seconds.
- Retrieving Relevant Results: Imagine the exact color, shade and design of curtains that fit your living room and then NOT having to go through thousands of product listings on amazon to find it !!
Pitfalls to Avoid: Discuss the risks and challenges of integrating generative AI into products, including hallucination, over-stepping domain boundaries, susceptibility to prompt hacking and injection attacks.
Security and Privacy: Discuss strategies to protect your AI models from malicious attacks and data breaches.
Performance Optimization: How to maximize accuracy and speed when integrating AI into your product.
Best Practices and Case Studies: Review effective strategies for applying generative AI in various applications, supplemented by real-world examples and case studies.

Target Audience:

This talk is aimed at product managers, software engineers, data scientists, and AI enthusiasts interested in understanding the practicalities of integrating generative AI into their products and services.

Outcome:

By the end of the talk, participants will have a deeper understanding of the intricacies of implementing generative AI models. They will be equipped with a practical guide to avoiding common pitfalls and applying effective strategies to build reliable, secure, and high-performing AI-powered solutions.

Looking forward to sharing these insights and sparking engaging discussions on how to navigate the fascinating yet complex landscape of AI integration.