How to Steal ChatGPT's Embedding Size and Other Low-rank Logit Tricks
Uncover hidden information about API-protected LLMs through low-rank logit analysis. Learn to estimate embedding sizes, audit model updates, and identify source models efficiently.
Informative Example Selection for In-Context Learning
Explore efficient approaches for selecting informative examples in In-Context Learning, enhancing large language model performance without additional training.
Unleashing the Value of Customer Intent with Intelligent Interventions
Explore AI/ML techniques to understand customer intent, reduce session abandonment, and enhance online retail experiences through data-driven interventions.
Stop Explaining Black Box ML Models for High Stakes Decisions and Use Interpretable Models
Explore the societal impact of black box ML models in high-stakes decisions and discover the benefits of using interpretable models for transparent decision-making.
Minimize Risk and Accelerate MLOps with ML Monitoring and Explainability
Discover strategies to minimize risk and accelerate MLOps through ML monitoring and explainability. Learn to efficiently monitor, troubleshoot, and document ML models for improved performance and compliance.
Implementing a Machine Learning Initiative: A Leader's Perspective
Discover key strategies for successfully implementing machine learning initiatives in organizations. Learn to align ML with strategic objectives, measure efforts, create a receptive culture, and navigate organizational dynamics.
An ML System for Radiotherapy Cancer Care - From Lab to Lives
Explore ML algorithm deployment for prostate cancer radiation therapy planning in a clinical study. Learn about evaluation methods, physician assessments, and real-world impact on patient treatment.
The Importance of Intelligibility in Machine Learning for Healthcare - Avoiding Black-Box Models
Explore intelligible machine learning models for healthcare, balancing accuracy and interpretability. Learn to understand, validate, and edit models for safe deployment in critical applications.
Using Reinforcement Learning in Large Scale Automation at Netflix
Optimize automation schedules and reduce failure detection time using self-service reinforcement learning tools. Learn from Netflix's applied RL service deployment experience.
Debugging for Math Lovers
Explore mathematical approaches to debugging, focusing on functional programming techniques and their impact on error resolution efficiency and program complexity reduction.
ROSiE: The Robot Operating System in Erlang - Implementation and Advantages
Explore ROSiE, an Erlang implementation of ROS, enabling BEAM-based interaction with robotics ecosystems. Learn its architecture, advantages, and witness live demonstrations including hot code upgrades on active robots.
Orthotope - APL-Inspired Arrays for Haskell - Lambda Days 2022
Explore Orthotope, a Haskell library for multi-dimensional arrays inspired by APL. Learn efficient structural operations, clever array representation, and various implementations for different storage and typing needs.
Formal Reasoning: An Alternative Approach to Formal Verification - Code BEAM America 2022
Explore formal reasoning techniques to improve system testing, monitoring, and design. Learn practical applications of formal verification concepts for more efficient software development and operations.
Time Travel Debugging in Production - Know Your Past to Predict Your Future
Explore time-travel debugging techniques for complex production systems, learn to build specialized debuggers, and understand their impact on system design for efficient troubleshooting.
Trace Specifications and Chaos Engineering: Advanced Testing with Snabbkaffe - Code BEAM Europe 2022
Explore advanced testing techniques for distributed Erlang applications using trace specifications and chaos engineering. Learn to verify complex scenarios and improve fault tolerance in production systems.
Evolving Erlang/OTP Feature by Feature - Selectable Features in OTP25
Explore Erlang/OTP's new selectable features, including Value-Based Error Handling. Learn how to evolve the language without affecting existing code, enabling experimentation with backwards-incompatible changes.
Learning Erlang and Elixir through Exercism and Advent of Code
Explore effective methods for learning Erlang and Elixir using Exercism and Advent of Code. Compare these resources, understand their strengths, and choose the best approach for your programming skill level.
Erlang for Untrusted Decentralized Systems
Explore Erlang's application in untrusted decentralized systems, covering HoneyBadgerBFT, threshold cryptography, distributed key generation, and P2P networking for multi-party collaboration.
Uncertainty and My Scientific Journey
Explore an academic's 15-year journey from grad school to tenured faculty, focusing on navigating uncertainty in research and career paths. Gain insights on managing mental stress in academia.
Secrets and Shadows: Leveraging Big Data for Vulnerability Discovery
Discover innovative approaches to large-scale vulnerability detection using unconventional data sources, focusing on forgotten cloud assets and leaked secrets to identify critical security weaknesses in major organizations.
Social Engineering with AI: From Traditional Attacks to Next-Generation Techniques
Discover how AI tools transform social engineering tactics, from crafting sophisticated phishing to conducting vishing operations, while learning both offensive techniques and defensive strategies for modern security awareness.