Chip has worked as a researcher at Netflix, was a core developer at NVIDIA (building NeMo, NVIDIA’s GenAI framework), and co-founded Claypot AI. She also taught Machine Learning at Stanford University.
Q: How would you define AI Engineer or AI Engineering?
A: It's a shift from more machine learning to more engineering and more product. Previously, building machine learning applications required building your own models with your own data and expertise. Now, you can use direct API calls.
Q: What are typical steps to build an AI application, from choosing a model through using RAG all the way to fine-tuning?
A: Start by understanding what makes a 'good' vs. 'bad' response. Build guidelines for the model, add examples, and evaluate using both automated metrics and human evaluations. Augment the context with documents (RAG pattern). Consider starting with keyword retrieval before jumping into embedding-based retrieval. When fine-tuning, be aware of the new problems that you need to deal with.
Q: What are practical ways for software Engineers to get started building AI applications?
A: Start with prompting and simple solutions before moving to advanced techniques. Data preparation can give a huge performance boost. If you have tried a lot of solutions already, and now you try Gen AI and you think this Gen AI is a solution for you, understand what makes a good response, then add examples.
Q: How did you write this book, how were you able to write a book about such a fast moving industry?
A: When you write a topic you're trying to bet on whether it's going to stay relevant in the future.
Focused on fundamentals that have been around for a while.
Determined if a problem is due to fundamental limitations of AI or current capabilities.
Q: Given that AI engineering moves so quickly, how did you ensure your book stays current?
A: Prioritised progress and future relevance over current trends. Focused on the underlying fundamentals rather than fleeting capabilities. Paid attention to whether advancements are due to fundamental limitations or temporary capabilities of AI, and how quickly capabilities are changing.
Q: What are the most common techniques used when building AI applications, things that a software engineer who's going into building AI applications should know about?
A: Techniques like RAG (Retrieval-Augmented Generation) and fine-tuning are useful. Focus on understanding what constitutes a good response. RAG is a powerful pattern, but don't jump straight to vector search; start with keyword retrieval.
Q: Given this rush to use Gen AI, what are your thoughts on staying focused on the problem?
A: The more we want to not miss out on things, the more things we will miss. Pick a problem that you care about and only focus on things that help you solve that problem. If some news comes out, ask if it helps solve the problem; if not, wait.
Q: When building an AI system, you need to evaluate the output. Why is it difficult to evaluate AI systems, and what are common ways to do that?
A: It's challenging because the smarter AI becomes, the harder it is for humans to evaluate. Use functional correctness to evaluate how well it performs a task. Use AI to evaluate other AI. Comparative evaluations can also be helpful. The quality of the AI judge depends on the underlying model and the prompt, and it is so non-deterministic.
Q: In evaluating AI, how do you prioritise users’ needs and experience?
A: Evaluate an application based on what users want. Go talk to users and look at their interactions. Manual data inspection has a high value-to-effort ratio. Measure what matters. Don't forget human evaluations.
Q: What are some common mistakes you've seen when teams are building AI applications?
A: Using Gen AI when you don't need it. Jumping straight to complex solutions or fancy agent frameworks.
Systematic thinking and problem-solving approaches usually don't change, even when technologies do. Don't use GenAI when you don't need GenAI
Q: Speaking of picking up new technology, as someone learning GenAI, a software engineer who wants to get into AI engineering, what would your recommendation be to learn?
A: Balance project-based learning with structured learning. Be able to stop and ask questions, and sometimes structured learning can help you ask the right questions. Pick a project, complement it with structured learning, and read papers. Tutorial based learning is great, but it is very important to be able to stop and ask questions.
Q: Will AI mean the end of software engineering?
A: AI can automate coding, but it won't fully automate problem-solving. Software engineering is about solving problems, not just the physical act of coding.
Q: What other use cases are you excited about for that AI could bring outside of just coding?
A: Education. Entertainment.
Q: What programming language did you use most when you built AI applications or did ML engineering?
A: Python and JavaScript.
Q: Which one is your favorite LLM model right now and why?
A: I don't really have a favorite.
Q: What are one or two books that you've read and would recommend?
Kai-Fu Lee, Chairman of Sinovation Ventures and author of AI Superpowers and AI 2041: Ten Visions for Our Future on the China-US AI Race Q: There's still a lot of challenges when it comes to the whole monetization of AI, according to his perspective. In the last three years, though, how have you looked at this whole evolution of China AI versus the US, and what are the advantages and challenges for China? A: Yeah, so firstly, I disagree on the prospects for the USA. USA because yes, you look at OpenAI, it's making half billion spending 40 billion. It looks like a bad balance sheet, but most of that 40 billion is spent for future revenues. And if you believe there are 2x, 3x, 5x growth for the next three years, it's going to justify that valuation at some point. The bubble is merely that it's gotten ahead of itself, not the likelihood of growth in the future. Not saying it's worth its price, right, but there's absolute substance under the thumb. Now back to t...
Grok , the AI model developed by Elon Musk's xAI, can understand when you type Indian languages like Hindi, Telugu, Odia or other Indian regional languages using English letters (like when you type 'namaste' instead of 'नमस्ते'), and it can respond by mixing English with those languages. Grok doesn't necessarily need the native script of these languages. It has natural language processing abilities that extend to multiple languages. This is great innovation because many people in India, especially in online communication, use transliteration. Grok can generate responses that combine English words and phrases with words and phrases from the regional language you used in your input. For example, if you ask a question using a mix of English and Telugu transliteration, Grok might respond with a sentence that includes both English and Telugu words. Check these Hindi, Telugu, Odiya samples - Grok, ab Hindi mein Grōk, ippuḍu telugulō Grok, Oḍiā re This way Grok is more...
Front-end leaders share their experience on pushing the boundaries of Web AI and run machine learning models entirely client side in the browser via JavaScript to get privacy, lower costs, and lower latency. From traditional AI models to Generative AI such as large language models (LLMs) and diffusion models, discover the latest advances of Web AI in 2024 that are accelerated by technologies such as WebAssembly, WebGPU, and WebNN.
Comments
Post a Comment