Building Developer Assistants that Think Fast and Slow
From Google TechTalks · 1:16:56
Show by Google TechTalks
A Google TechTalk, presented by Mayur Naik, 2022/05/19Abstract: Prevalent developer assistants are either conventional "slow-thinking" tools based on logic reasoning, or emergent "fast-thinking" tools based on deep neural models trained on enormous amounts of code. In this talk, I will survey the strengths and limitations of these two classes of tools, and propose a new approach which combines their benefits without suffering from their drawbacks.Uploaded 24-05-22About the Speaker: Mayur Naik is Professor of Computer and Information Science at the University of Pennsylvania. His research lies at the intersection of programming languages and machine learning, with a current emphasis on neurosymbolic programming. He received a Ph.D. in Computer Science from Stanford University in 2008.
More episodes of Google TechTalks
More episodes
- Threat Models for Memorization: Privacy, Copyright, and Everything In-Between
- Technology Assisted Reading Acquisition: Children Acquiring Literacy Naturally
- sex on the internet, the realities of porn, sexual privacy,
- Privacy Auditing of Large Language Models
- The Limits and Possibilities of One Run Auditing
- PhotoTechEDU Day 29: Photographing VR Panoramas
- Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
- Inside VMware Fusion
- Java Posse Episode 100 (Live Special)
- Cascading Adversarial Bias from Injection to Distillation in Language Models
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.