Publishing Details
Contact & Outreach
About This Podcast
https://www.domainshift.ai
Explore Statistics
Recent Episodes
AI Alignment
Understand the crucial process of ensuring AI systems behave consistently with human values, goals, and ethical principles.
Constitutional AI
Explore Anthropic's method for training AI systems using a constitution of rules and principles for self-critique and alignment.
Human-in-the-Loop (HITL)
Discover how humans collaborate with AI in training, evaluation, and operation to enhance accuracy, reliability, and adaptability.
Agent Frameworks
Understand the SDKs and libraries providing tools to build, manage, and deploy autonomous AI agents with pre-built components.
Model Context Protocol (MCP)
Learn about Anthropic's open protocol standardizing how applications provide context to LLMs—the "USB-C for AI applications."
Spiking Neural Networks (SNNs)
Explore neural networks that transmit information through timed spikes, more closely mimicking biological neurons for energy-efficient computation.
Neuromorphic Computing
Discover computer engineering modeled after the human brain and nervous system, creating devices that learn and adapt like biological systems.
xLSTM (Extended Long Short-Term Memory)
Learn about the enhanced LSTM architecture with exponential gating and modified memory structures for improved scalability and performance.
Linear Transformers
Explore transformers that replace softmax attention with linear attention functions, reducing complexity from quadratic to linear.
Hyena
Discover a subquadratic-time replacement for attention using long convolutions and gating, enabling processing of extremely long sequences.
RetNet (Retentive Network)
Understand a foundation architecture balancing training parallelism, low-cost inference, and performance through flexible retention mechanisms.
RWKV (Receptance Weighted Key Value)
Learn about an architecture combining transformer parallelizable training with RNN efficient inference through linear attention mechanisms.
Mamba
Explore a selective State Space Model that addresses transformers' quadratic bottleneck with linear scaling and significantly faster inference speeds.
State Space Models (SSMs)
Discover models inspired by control theory that provide an efficient alternative to transformers for handling long-range dependencies in sequential data.
Switch Transformers
Understand how this architecture uses a single-expert routing mechanism to scale models to trillions of parameters efficiently.
Mixture of Experts (MoE)
Learn about an architecture that divides neural networks into specialized sub-networks, enabling massive scale without proportional computational cost.
Small Language Models (SLMs)
Explore compact AI models with millions to billions of parameters, designed for efficient deployment on edge devices and resource-constrained environments.
Vision-Language-Action (VLA) Models
Discover multimodal foundation models that integrate vision, language, and action to enable robots to perceive, understand instructions, and execute physical tasks.
Physical AI
Discover how AI enables autonomous systems to perceive, understand, and perform complex actions by incorporating spatial relationships and physical laws.
Embodied AI
Learn about the integration of artificial intelligence into physical systems like robots, enabling them to perceive, reason, and act in the real world.
Frequently Asked Questions
Talk AI To Me has published 106 episodes since October 2025, covering topics in Technology.
Talk AI To Me is currently sporadic with new episodes every few days. Average episode length is 2m.
Sign up on Grep.FM to access contact details for Talk AI To Me, including email and social media links.
