OpenCancer AI: Fight Cancer with AI

OpenCancer AI: Fight Cancer with AI

"Find what your treatment plan might be missing. In minutes, not weeks. Built by a survivor."Ari Akerstein has embarked on a mission to help connect people in cancer treatment. They help patients find the best treatment options, as well as connect to a community. It is inspiring work, and incredible to see.OpenCancer.ai gives superpowers to every cancer patient. Clinically trained AI tools: second opinions, records translation, clinical trial matching, expert review - all grounded in the latest guidelines and their own medical records. Co-founded by two cancer survivors.For partners, we deliver qualified, high-intent patients at the moment of clinical decision. We don't sell data. We route intent to the most relevant services at the moment it matters most.

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

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

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.

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