Will AI Snap That with Thanos and Rollins

Thanos Diacakis, Michael Rollins

0,0 (0)
ACTUALITÉS TECHNOLOGIQUES
CHAQUE SEMAINE

Thanos and Rollins weekly discuss if and how AI will disrupt current jobs

-4 J

Taming AI Context Chaos: How Epic Scale AI Ships Faster with MCP

00:00 Cold open: “Humans of Earth” intro 00:38 Meet the guest: Colin Masters (Epic Scale AI) 02:40 Colin’s origin story (military → construction → NYSE → dev) 04:00 The EPIC method: Explore–Plan–Implement–Check 05:40 Context isn’t a dump: vector DB + forced session search 06:20 Plans = branches (GitHub issues integration) 07:10 Memory bank: standardize decisions (deposits vs withdrawals) 08:40 Feedback to feature: free tier shipped in 3 hours 10:00 Shared vs project context; 30 MCP tools 11:10 Using AI since 2024; choose simple over complex 12:20 Explore phase prompts → define a shippable MVP 13:10 AI-first ops: branches, artifacts, and shared context 14:20 Context bloat and model limits 15:05 The Claude 4.5 rant (pain points) 16:10 Buy vs build: why consider Epic Scale 17:10 Why “last 20 commits” isn’t enough 18:00 Semantic tasks and progress tracking 19:10 Watching cross-branch changes 20:00 Agent loops—with human review 21:00 Human-in-command: no auto-approve 22:10 Quote: “Developers in control of their tools will succeed.” 23:40 Houses vs software: constraints and collaboration 29:10 Where Epic Scale shines (small teams 10) 32:00 Status without Big‑A Agile: stakeholder visibility 34:10 Failing as a learning loop 38:10 Mindset shift: embrace AI or get left behind 39:20 Where AI beats humans (YAML, cross-file reasoning) 41:10 Juniors are crushing it; Go‑to‑Market Engineer 44:00 Speed breaks sales/support; training new grads 47:00 Where to find Epic Scale + free tier note 47:40 OutroAI dev isn’t “dump more into the context window.” Colin Masters from Epic Scale AI breaks down how the EPIC method (Explore–Plan–Implement–Check), an MCP server, and a shared vector memory turn chaos into shipping velocity—especially for small, AI‑first teams.We get practical about plans-as-branches with GitHub issues, memory banks to stop re‑deciding decisions, why auto‑approve wrecks projects, and how a user comment led to a free tier in three hours. We also debate “houses vs software,” the rise of the Go‑to‑Market Engineer, and what juniors are getting right with AI.Recorded: October 14, 2025What you’ll learn:How to replace “tickets” with plans-as-branches and keep context cleanWhy vector DB + retrieval beats giant context windowsGuardrails for agent loops (human-in-command, no auto‑approve)Where AI truly outperforms humans (cross-file reasoning, YAML, refactors)Team shape for AI‑first orgs (small, sharp, 10)How to create stakeholder visibility without Big‑A Agile ceremonyGuestColin Masters — Epic Scale AI: https://epicscale.ai/Chapters See chapter markers above.Subscribe for more on AI engineering, MCP, and practical agent workflows.Hashtags: #AIEngineering #MCP #DevTools #AIFirst #VectorDB #VSCode #GitHub

49 min
14 OCT.

Sonnet 4.5 Sucks (says Rollins)

Debating AI Models and Efficient Workflow Management with Michael Rollins and ThanosIn this episode, Michael Rollins and his co-host Thanos discuss their experiences and frustrations with various AI models, specifically critiquing Sonnet 4.5 and GPT-5. They delve into the technical details of setting up PR environments using AWS Fargate and Terraform, and how these tools are integrated into their current workflow. The episode also touches on the challenges of maintaining code quality and documentation in a fast-paced development environment. Notably, they reflect on the evolving role of engineers in the context of advancing AI capabilities and consider the implications for future project management and costs.00:00 Introduction and Today's Topics00:11 Debating the Merits of Sonnet 4.501:51 Setting Up PR Environments with Fargate05:12 Challenges with AI Models14:33 Managing Large Codebases and PRs18:42 Empowering Engineers with Broader Scopes22:15 Introduction to Documentation Practices22:41 Artifact Requirements and Agile Integration23:54 Challenges and Future of Documentation24:45 Using Issues and Repositories as Source of Truth25:44 Improving Code Documentation with AI26:30 Exploring Mermaid Diagrams and Figma28:56 Understanding Claude and Its Naming08:08 Discussion on PRDs and Plans32:14 Token Usage and Cost Management34:44 Engineer Independence and Implementation40:52 Concluding Thoughts and Future Plans

45 min
22 SEPT.

Mike Needs AI Therapy from Thanos - Will AI Snap That?

In this episode of 'Will AI Snap That,' host Michael Rollins, alongside his therapist Thanos, delves into the complexities of managing AI and engineering projects. Michael discusses the challenges he's facing as the bottleneck in his current project, where the rapid pace of development and code reviews is overwhelming. The conversation covers optimizing PR reviews, managing database migrations, and the integration of automated tools to streamline processes. They also explore the importance of defining clear guidelines and the role of AI in code quality checks. With humorous anecdotes and technical insights, this episode sheds light on maintaining efficiency without compromising quality in fast-moving engineering environments.

42 min
15 SEPT.

Agile is Dead, the Intern Killed It

The Death of Agile and the Rise of AI in Software DevelopmentIn this episode of 'AI Snap That,' hosts Michael Rollins and Thanos discuss the provocative statement that 'Agile is dead,' particularly critiquing the rigid and ceremonial aspects of Agile with a capital 'A.' They explore how small 'a' agile principles still hold value. They delve into their personal experiences and methodologies in software development, including leveraging AI tools for coding and project management. Despite advancements, they stress the importance of traditional software engineering fundamentals. The episode also features discussions about enhancing productivity with a small engineering team, automation in code reviewing, and the balance between human oversight and AI's capabilities in software development.00:00 Introduction and Hosts00:09 Agile is Dead: The Bold Claim00:42 Defining Agile: Big A vs. Small a01:34 The Problems with Big A Agile01:49 Small a Agile: A Reasonable Approach06:12 Agile vs. Waterfall: A Historical Perspective07:14 AI Scrum Master: A Futuristic Idea08:11 The Role of Engineers in Agile14:41 Challenges of Agile Ceremonies17:11 Intern's Journey: From Fear to Freedom23:42 Reflections on Process and Productivity24:17 Challenges of Team and Architecture Changes25:03 Rewriting the Machine Learning Pipeline26:53 Empowering New Engineers27:34 Automating Code Review and Testing34:20 Implementing Standard Artifacts39:45 Ensuring System Reliability46:52 Final Thoughts and Future Plans

49 min
25 AOÛT

Are New Grads Screwed?

Navigating the Future Job Market: Opportunities and Challenges in the Age of AIJoin hosts Michael Rollins and Sean Byrnes as they explore the impact of AI on the job market in this insightful episode of 'AI Snap.' With a focus on new graduates and career paths, the discussion delves into the dislocations caused by technological advancements, overhiring trends, and the pandemic. They provide practical advice for new grads, highlighting the importance of adaptability, creative thinking, and the value of networking. Drawing from personal experiences and industry insights, Rollins and Burns offer a hopeful perspective on how to succeed in an evolving job market shaped by AI.00:00 Introduction and Welcome00:26 Nostalgia: Early Days of Podcasting01:03 The Impact of AI on Jobs02:04 Career Advice for the Next Generation04:50 Challenges in the Job Market06:28 The Role of AI in Job Displacement08:04 Navigating the New Job Landscape12:30 Innovative Solutions for New Grads15:20 Rethinking Career Paths20:20 The Value of Initiative and Adaptability27:08 Applying School Rigor to Career Development27:52 Networking and Making Connections29:35 Changing Career Paths and Market Dynamics31:53 Impact of Technological Shifts on Careers37:21 Outsourcing and Automation in Business41:23 Adapting Skills to New Opportunities50:01 Navigating Career Challenges and Finding Hope

55 min
11 AOÛT

Agents All the Way Down! - What's up with AI agents?

Navigating the Rise of Multi-Agent AI SystemsIn this episode of 'I Snap That,' hosts Michael Rollins and Thanos discuss their experiences and insights into the development and challenges of using multi-agent AI systems versus single-core LLM agents. While Thanos shares his recent travels in Greece and upcoming vacation plans, Michael dives deep into the complexities of AI coordination, the Blackboard model, and the surprising efficiency gains realized through distributing tasks among specialized AI agents. They explore the counterintuitive nature of these improvements, the role of memory and semantic understanding in AI workflows, and touch upon future concerns about QA and ensuring trust in AI outputs. The episode balances technical discussions with light-hearted banter and real-world anecdotes, creating an informative and engaging dialogue about the evolving landscape of AI technology.00:00 Welcome to I Snap That!00:30 Vacation Plans and Travel Stories04:27 Exploring AI Agents06:42 The Blackboard Model Explained11:00 Memory and Data Coordination15:08 Building and Testing Multi-Agent Systems20:02 Performance and Efficiency Insights23:04 Token Usage and Trade-offs in Computer Science24:30 Challenges with Coding Agents and Data Access25:57 Handling Semi-Structured Data and CSV Ambiguities27:20 Improving Coding Agents with MCP Servers32:12 Ensuring Trust and QA in AI Systems39:24 Learning and Implementing Lang Graph42:13 Real-World Coding Agent Experiences46:08 Concluding Thoughts and Future Topics

47 min
28 JUIL.

Is Anthropic at War?

Surviving the Robotic Apocalypse: Is Anthropic at War?!?!In this episode of 'AI Snap That,' hosts Michael Rollins and Thanos discuss their personal experiences with kitesurfing, wakeboarding, and snowboarding injuries before diving into the intriguing world of AI developments and dramas. They delve into the financial troubles and pricing strategies of AI giants Anthropic and Cursor, exploring how these companies are trying to navigate their cash flow challenges. The conversation touches upon the recruitment dynamics within these companies, egos in Silicon Valley, and the role of anthropic's Claude Code in the evolving landscape of AI tools. Michael and Thanos also ponder the broader implications of AI in coding, best practices for team productivity, and whether standardizing AI tools is beneficial. Tune in for a unique mix of personal anecdotes, industry insights, and thought-provoking discussions on the future of AI and technology.

53 min
14 JUIL.

Can We Make R2 for Planes?!?! w/ SavvyAviation

Will AI Transform General Aviation? Insights with Savvy Aviation's Tech ExpertsIn this episode, Michael Rollins and Thanos are joined by Chris and Adam from Savvy Aviation to explore the intersection of AI and aviation. They discuss how Savvy Aviation helps aircraft owners manage maintenance through machine learning and data analytics. The conversation dives into predictive models for engine health, the future application of large language models (LLMs) for maintenance logs, and the potential for AI-assisted inflight tools. They also touch on the evolution of AI terminology, the challenges of false positives, and possible future developments in the field.00:00 Introduction and Welcome00:14 Meet the Savvy Aviation Team00:38 Chris's Role and Background01:54 Adam's Role and Background03:36 AI in Aviation Maintenance06:08 Machine Learning and Data Analysis07:37 Viva and Predictive Maintenance11:43 Future of AI in Aviation17:08 Combining Machine Learning and LLMs27:19 False Positives in Aviation28:49 Acceptable Levels of Certainty29:40 Pilot's Role and Digital Tools31:49 AI in General Aviation34:21 Personal Flying Experiences38:29 Internet Connectivity in Private Planes46:23 Machine Learning in Aircraft Maintenance

45 min

Tout afficher (28)

Thanos and Rollins weekly discuss if and how AI will disrupt current jobs

Création

Thanos Diacakis, Michael Rollins
Années d’activité

2 k
Épisodes

28
Classification

Tous publics
Copyright

© Thanos Diacakis, Michael Rollins
Site web de l’émission

Will AI Snap That with Thanos and Rollins