Agentic Conversations (formally mlops.community)
Demetrios
Episodes
-
LLM Search, UI/UX challenges, Context Engineering and the 80/20 of Eval
Context Engineering is more crucial than Prompt Engineering; relevant context enhances AI performance.
-
The Era of AI Agents in Marketing // Joel Horwitz // #337
AI agents are revolutionizing marketing by enabling personalized and scalable outreach.
-
Distilling 200+ Hours of NeurIPS: What’s Next for AI // Nikolaos Vasiloglou // #336
AI plays an increasingly important role in synthesizing complex academic research, particularly in events like NeurIPS.
-
Building Coding Agents: Design Decisions, Prompting Tricks, GUI Anti-patterns
The efficiency of code generation has drastically improved with the introduction of coding agents like AMP, with users generating up to 95% of their code automatically.
-
A Candid Conversation with the CEO of Stack Overflow
Stack Overflow is adapting to the AI era by licensing its data and expanding beyond traditional Q&A.
-
Knowledge is Eventually Consistent // Devin Stein // #335
Code functions as a reliable system of record, reflecting product functionality and changes.
-
LinkedIn Recommender System Predictive ML vs LLMs
LLMs can automatically interpret user signals, reducing the need for detailed feature engineering in recommendation systems.
-
GPU Considerations, Labeling Privacy, Rapid Fine Tuning, and the Role of Private Eval Pipelines to Benchmark New Models
AI models are rapidly evolving, making ongoing evaluation crucial.
-
The Hidden Bottlenecks Slowing Down AI Agents
The primary bottleneck in AI agent development is not the tools but the creation and management of effective evaluation datasets.
-
9 Commandments for Building AI Agents
Building AI agents requires a clear understanding of user needs and context, which helps reduce cognitive load and improves the utility of the agent.
-
Enterprise AI Adoption Challenges
Successful AI adoption in enterprises requires a cultural shift that encourages experimentation and learning.
-
Real-time Feature Generation at Lyft // Rakesh Kumar // #334
Real-time feature generation is crucial for maintaining accurate marketplace data for Lyft.
-
AI Agent Development Tradeoffs You NEED to Know
AI agents like Alice and Julian are transforming sales outreach by automating complex tasks.
-
From the Legal Trenches to Tech // Nick Coleman // #332
Social Security disability advocacy is a complex field, requiring extensive documentation and legal expertise to navigate claims effectively.
-
The Rise of Sovereign AI and Global AI Innovation in a World of US Protectionism // Frank Meehan // MLOps Podcast #331
Sovereign AI is essential for national security, enabling governments to control their own data and AI infrastructure.
-
A New Way of Building with AI
AI is moving towards automating everyday tasks effectively, aiming for practical applications that work seamlessly with users.
-
Inside Uber’s AI Revolution - Everything about how they use AI/ML
Michelangelo is Uber's innovative ML platform, centralizing model management for various applications.
-
The Missing Data Stack for Physical AI
Physical AI has the potential to transform industries by allowing real-world interactions.
-
AI Reliability, Spark, Observability, SLAs and Starting an AI Infra Company
Data infrastructure is evolving, and existing tools are no longer sufficient to meet modern day demands.
-
Greg Kamradt: Benchmarking Intelligence | ARC Prize
Effective AI benchmarks should cater to challenges that humans find easy but are complex for AI.
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account