Programmers Apprentice Season 2: Future Directions in AI-assisted Coding Erik Meijer YOW! 2023

This presentation was recorded at YOW! Australia 2023. #GOTOcon #YOW Erik Meijer - Director of Engineering at Facebook; “Think Like A Fundamentalist, Code Like A Hacker“ ORIGINAL TALK TITLE The Programmer’s Apprentice Season 2: Advancements and Future Directions in AI-assisted Coding RESOURCES ABSTRACT In 1976, Charles Rich and his colleagues pioneered the concept of a programmer’s apprentice – an interactive programming system designed to assist expert programmers in the design, coding and maintenance of large and complex programs. The idea of a digital prosthesis, extending our biological brain to seamlessly bridge the gap between our ideas and the code we produce, has been revisited multiple times throughout the years. For instance, the Probability/Bigcode team has spent over half a decade applying machine learning to enhance efficiency for engineers, data scientists and systems across the board. Historically, these endeavors relied on traditional (symbolic) AI techniques or early-stage neural net models, resulting in limited success in meeting the high expectations. However, the emergence of generative models like GPT has transformed what was once considered science fiction into reality, rendering the need for custom model architectures and embeddings obsolete. Consequently, many developers are now incorporating AI-based ‘co-pilots’ into their daily programming routines. In this talk, we’ll explore the various ways AI has been applied at Meta, such as code search, code recommendations and bug fixing, and revisit these areas in the context of large language models (LLMs). Additionally, we’ll discuss our vision for the future of generative AI in productivity tools, pivoting from a collection of task-specific tools designed for a generic user base to a single, user-specific tool capable of tackling a multitude of tasks. This transition will illuminate the ongoing evolution of AI-assisted programming and its potential impact on the developer community and beyond. [...] TIMECODES 00:00 Intro 05:23 Non-monotonic logic 07:57 Virtuous cycle 08:48 Vicious cycle 11:44 AI in software engineering at Facebook 12:44 Code searching using natural language 14:58 Code recommendations 15:59 Automated bug fixing 20:48 Let’s automate ourselves away & have fun doing it 35:26 LLM as scripting client 41:49 LLM-based software is very powerful, but... 45:19 Outro Read the full abstract here: RECOMMENDED BOOKS Alex Castrounis • AI for People and Business • Phil Winder • Reinforcement Learning • Holden Karau, Trevor Grant, Boris Lublinsky, Richard Liu & Ilan Filonenko • Kubeflow for Machine Learning • Kelleher & Tierney • Data Science (The MIT Press Essential Knowledge series) • Lakshmanan, Robinson & Munn • Machine Learning Design Patterns • Lakshmanan, Görner & Gillard • Practical Machine Learning for Computer Vision • Aurélien Géron • Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow • #LLM #AIAssistedCoding #DataScience #ChatGPT #GPT4 #GenAI #GenerativeAI #SoftwareEngineering #Programming #ArtificialIntelligence #MachineLearning #LargeLanguageModels #FutureOfWork #Hinton #GeoffreyHinton #RichardFeynman #Feynman #ParetoPrinciple #Pareto #ErikMeijer #YOWcon Looking for a unique learning experience? Attend the next GOTO conference near you! Get your ticket at Sign up for updates and specials at SUBSCRIBE TO OUR CHANNEL - new videos posted almost daily.