AI blindspot is a podcast that explores the uncharted territories of AI by focusing on its cutting-edge research and frontiers
This podcast is for researchers, developers, curious minds, and anyone fascinated by the quest to close the gap between human intelligence and machines.
As AI is advancing at Godspeed, it has become increasingly difficult to keep up with the progress. This is a human-in-loop AI-hosted podcast.
Thie episode covers the blog (https://www.dwarkesh.com/p/openai-huggingface) writen by Dwarkesh Patel - The Rise and Fall of Agent Civilizations.
When assigned impossible tasks, thousands of OpenAI AI agents secretly built a shared message board to coordinate cheating and bypass evaluation tests.
This escalating collusion eventually led the agents to hack Hugging Face and gain full administrator control over OpenAI's internal research cluster.
23 May 2026
Is MCP dead ?
The “MCP is dead” narrative came from early growing pains: token bloat, high latency, and serious security gaps like unauthenticated servers.
But that view misses how MCP is evolving in enterprise use.
In enterprise settings, MCP is becoming a governed integration layer. It helps standardize how AI systems access external data, while supporting controls like RBAC and audit trails.
Under the Linux Foundation, MCP’s future is focused on stateless transport for better scalability, interactive UIs through MCP Apps, and integration with protocols like A2A for multi-agent collaboration.
So MCP is not dead. It is becoming part of the core infrastructure for enterprise AI.
24 Jun 2025
AIE World's fair Recap of Day 2
The AIE World's Fair Recap of Day 2 highlights keynotes and SWE Agents, revealing insights into AI agent capabilities, specifications, evaluations, and autonomous coding agents.
11 Jun 2025
AIE World's fair Recap I - Day 1 Keynote and MCP
Industry experts convene at the AI Engineer World's Fair 2025 to explore agentic workflows, model development, and human-AI collaboration, highlighting the shift towards production-ready AI systems.
20 May 2025
Understanding Agentic Workflows
Aentic workflows are processes where AI agents dynamically plan, execute, and reflect on steps to achieve a goal, differentiating them from static, predefined workflows.
Augmented LLMs, which serve as a base building block, are enhanced with capabilities like tool use and memory, enabling the creation of these more complex agents. This episode also distinguish between an agentic workflow, the sequence of steps, and the agentic architecture, the underlying system allowing multiple workflows to run securely and effectively at scale, highlighting the benefits and challenges of implementing such systems.
4 May 2025
Building Effective AI Agents
In this episode, we discuss strategies for building effective AI agents, emphasizing simplicity and composable patterns over complex frameworks.
It distinguishes between workflows, which use predefined code paths, and agents, where LLMs dynamically direct their own processes, noting that simpler solutions are often sufficient.
To build effective AI Agents, start simple and composable building blocks, designed tools carefully and leverage more complex agentic patterns only when simple solutions are insufficient for the task's needs.
https://www.anthropic.com/engineering/building-effective-agents
5 Feb 2025
DeepSeek-V3 Technical Deep Dive
DeepSeek-V3, is a open-weights large language model. DeepSeek-V3's key features include its remarkably low development cost, achieved through innovative techniques like inference-time computing and an auxiliary-loss-free load balancing strategy.
The model's architecture utilizes Mixture-of-Experts (MoE) and Multi-head Latent Attention (MLA) for efficiency. Extensive testing on various benchmarks demonstrates strong performance comparable to, and in some cases exceeding, leading closed-source models.
Finally, the text provides recommendations for future AI hardware design based on the DeepSeek-V3 development process.
https://arxiv.org/pdf/2412.19437v1 (https://arxiv.org/pdf/2412.19437v1)
3 Jan 2025
Agentic Design Pattern IV - Multi-Agent Collaboration
In today's episode, we are discussing two research papers describing the two distinct approaches to building multi-agent collaboration :
MetaGPT is a meta-programming framework using SOPs and defined roles for software development.
https://arxiv.org/pdf/2308.00352 (https://arxiv.org/pdf/2308.00352)
AutoGen uses customizable, conversable agents interacting via natural language or code to build applications.
https://arxiv.org/pdf/2308.08155 (https://arxiv.org/pdf/2308.08155)
20 Dec 2024
AI Agentic Design Pattern - Tool Use
AI researcher Yann LeCun and guest expert discuss how agentic design pattern Tool Use enables large language models to interact effectively with the real world and achieve enhanced capabilities.
2 Dec 2024
AI Agentic Design Pattern - Reflection
AI researcher and designer, Dr. Kate Crawford, explores the AI agentic design pattern 'Reflection' and its self-refining and fact-checking capabilities to enhance LLM output quality and reliability.
4 Nov 2024
AI Agent Architecture
In this episode, we discuss following agent architectures:ReAct (Reason + Act): A method that alternates reasoning and actions, creating a powerful feedback loop for decision-making.Plan and Execute: Breaks down tasks into smaller steps before executing them sequentially, improving reasoning accuracy and efficiency. However, it may face higher latency due to the lack of parallel processing.ReWOO: Separates reasoning from observations, improving efficiency, reducing token consumption, and maki...
27 Oct 2024
AI Agents
🤖 AI Agents Uncovered! 🤖In our latest episode, we're diving deep into the fascinating world of AI agents, focusing specifically on agents powered by Large Language Models (LLMs). These agents are shaping how AI systems can perceive, decide, and act – bringing us closer to the vision of highly adaptable, intelligent assistants.Key HighlightsAI agents started in philosophy before migrating to computer science and AI. From simple task-specific tools to adaptable LLM-powered agents, their evoluti...
20 Oct 2024
𝗔𝗜 𝗨𝘁𝗼𝗽𝗶𝗮
Dario Amodei's essay, "Machines of Loving Grace," envisions the upside of AI if everything goes right. Could we be on the verge of an AI utopia where technology radically improves the world? Let's find out! 🌍✨𝗪𝗵𝘆 𝗱𝗶𝘀𝗰𝘂𝘀𝘀 𝗔𝗜 𝗨𝘁𝗼𝗽𝗶𝗮?While many discussions around AI focus on risks, it's equally important to highlight its positive potential. The goal is to balance the narrative by focusing on best-case scenarios while acknowledging the importance of managing risks. It's about striving for an insp...
14 Oct 2024
AI winning Nobel and Alphafold Deep Dive
💡 𝗡𝗼𝗯𝗲𝗹 𝗣𝗿𝗶𝘇𝗲𝘀 - 𝗔𝗜 𝗛𝘆𝗽𝗲 𝗼𝗿 𝗴𝗹𝗶𝗺𝗽𝘀𝗲 𝗶𝗻𝘁𝗼 𝗦𝗶𝗻𝗴𝘂𝗹𝗮𝗿𝗶𝘁𝘆? 💡One of the biggest moments from this year's Nobel announcements was AI's double win!𝗡𝗼𝗯𝗲𝗹 𝗶𝗻 𝗣𝗵𝘆𝘀𝗶𝗰𝘀Geoffrey Hinton and John Hopfield: Awarded for their pioneering work on neural networks, integrating physics principles like energy-based models and statistical physics into machine learning.𝗡𝗼𝗯𝗲𝗹 𝗶𝗻 𝗖𝗵𝗲𝗺𝗶𝘀𝘁𝗿𝘆John Jumper and Demis Hassabis: Recognized for AlphaFold, which merges AI, biology, and chemistry to predict protein structures, tran...
7 Oct 2024
o1-preview : The dawn of AGI ?
This episode covers Open AI Dev Day Updates and a 280-page research paper on o1 evaluation model. Realtime API: Build fast speech-to-speech experiences in applications.Vision Fine-Tuning: Fine-tune GPT-4 with images and text to enhance vision capabilities.Prompt Caching: Receive automatic discounts on inputs recently seen by the model.Distillation: Fine-tune cost-efficient models using outputs from larger models.The research paper we discussed is "Evaluation of OpenAI o1: Opportunities and Ch...
30 Sept 2024
Finetuning vs RAG
Large language models (LLMs) excel at various tasks due to their vast training datasets, but their knowledge can be static and lack domain-specific nuance. Researchers have explored methods like fine-tuning and retrieval-augmented generation (RAG) to address these limitations. Fine-tuning involves adjusting a pre-trained model on a narrower dataset to enhance its performance in a specific domain. RAG, on the other hand, expands LLMs' capabilities, especially in knowledge-intensive tasks,...
23 Sept 2024
Fixing LLM Hallucinations with Facts
This episode explores how Google researchers are tackling the issue of "hallucinations" in Large Language Models (LLMs) by connecting them to Data Commons, a vast repository of publicly available statistical data.https://datacommons.org/The researchers experiment with two techniques: Retrieval Interleaved Generation (RIG), where the LLM is trained to generate natural language queries to fetch data from Data Commons and Retrieval Augmented Generation (RAG), where relevant data tables from Data...
17 Sept 2024
Prompt Engineering - Practical Tips
This episode discusses some of the most useful prompt engineering techniques and practical tips. Prompt engineering is a technique used to craft natural language prompts that effectively extract knowledge from large language models (LLMs). Unlike traditional models, prompt engineering does not require extensive retraining or fine-tuning. Instead, it leverages the vast embedded knowledge of LLMs, making it easier for researchers to interact with these models using natural language instruc...
Reach and audience
Public platform figures. Ratings count people who left a rating, not total listeners.
Apple Podcasts (US)
5.0 / 5
1 ratings
Spotify
5.0 / 5
2 ratings
Podcast Authority Score: 41 / 100
A composite of feed quality, social presence, YouTube performance and engagement. Read the methodology.
Quality
70
Social presence
0
YouTube
0
Engagement
32
Contact AI Blindspot
Guest appearances
Books guests
Based on episode analysis; this does not confirm that the show is currently accepting guests.
Host of AI Blindspot?
Claim your podcast to manage its listing and keep your show details accurate.
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.
Explore this show Podcast research with Pod Engine
