Agentic Conversations (formally mlops.community)
Demetrios
Episodes
-
Insights from Cleric: Building an Autonomous AI SRE // Willem Pienaar // #290
The transition from development to production poses significant challenges in AI SRE due to a lack of curated problem-solution datasets.
-
Robustness, Detectability, and Data Privacy in AI // Vinu Sankar Sadasivan // #289
Watermarking alone is not a fully reliable method for detecting AI-generated content, and there's currently no foolproof detection technique available.
-
AI & Aliens: New Eyes on Ancient Questions // Richard Cloete // #288
AI is fundamental in processing large volumes of data for detecting UAPs and classifying astronomical objects.
-
Real LLM Success Stories: How They Actually Work // Alex Strick van Linschoten // #287
The consolidation of LLM use cases provides a valuable resource for understanding diverse applications and implementations.
-
Navigating Machine Learning Careers: Insights from Meta to Consulting // Ilya Reznik // #286
Fine-tuning models can often be counterproductive; consider alternative methods like prompt engineering first.
-
Collective Memory for AI on Decentralized Knowledge Graph // Tomaž Levak // #285
Decentralized knowledge graphs enhance transparency and data integrity.
-
Efficient Deployment of Models at the Edge // Krishna Sridhar // #284
AI is rapidly evolving, with significant focus on deploying models at the edge rather than relying solely on cloud computing.
-
Real World AI Agent Stories // Zach Wallace // #283
Efficiency in data integration is crucial to the success of AI applications.
-
Machine Learning, AI Agents, and Autonomy // Egor Kraev // #282
Egor Kraev has played a pivotal role in leveraging AI at Wise to enhance their operations in various domains including fraud detection and marketing.
-
Re-Platforming Your Tech Stack // Michelle Marie Conway & Andrew Baker // #281
A strategic move to the cloud can significantly enhance operational efficiency, as demonstrated by the reduction in model run times from hours to minutes.
-
Holistic Evaluation of Generative AI Systems // Jineet Doshi // #280
Evaluating generative AI systems is critical for building trust but remains an open challenge due to the complexity and flexibility of LLMs.
-
Unleashing Unconstrained News Knowledge Graphs to Combat Misinformation // Robert Caulk // #279
Knowledge graphs can dynamically represent relationships, leading to a nuanced understanding of complex narratives.
-
LLM Distillation and Compression // Guanhua Wang // #278
DeepSpeed and Domino represent significant advances in making large language model training more efficient by addressing communication overhead.
-
LLM Distillation and Compression // Guanhua Wang // #278
Not summarized yet
-
AI's Next Frontier // Aditya Naganath // #277
Not summarized yet
-
AI's Next Frontier // Aditya Naganath // #277
The competition in AI investment is fierce, requiring unique value propositions from startups.
-
PyTorch for Control Systems and Decision Making // Vincent Moens // #276
Benchmarking your code is essential; understanding the performance impacts of using techniques like pin memory can mitigate common inefficiencies.
-
AI-Driven Code: Navigating Due Diligence & Transparency in MLOps // Matt van Itallie // #275
Code-based scans assess multiple dimensions of a codebase, crucial for technical due diligence.
-
PyTorch's Combined Effort in Large Model Optimization // Michael Gschwind // #274
Collaboration is essential for driving advancements in AI and optimizing models.
-
LLMs to agents: The Beauty & Perils of Investing in GenAI // VC Panel // Agents in Production
AI agents are redefining customer service, enabling 24/7 support and relieving human agents of routine tasks.
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account