Published 16 Feb 2026
Duration: 00:49:17
Joe McCormick adapts to his vision impairment caused by Leber's hereditary optic neuropathy by leveraging AI tools, including a Slack summary Chrome extension and coding tools like Claude Code and VS Code, to improve accessibility and efficiency in his work and daily life.
Joe McCormick is a principal software engineer at Babylist who lost most of his central vision due to a rare genetic disorder right before starting co...
The podcast explores Joe McCormick's journey with vision impairment caused by Lieber's hereditary optic neuropathy and his shift from robotics to computer science. He discusses how he uses AI tools to improve both his professional work and personal life, particularly through accessibility features such as image description and spell checking extensions. These tools are designed to support users with visual impairments by providing auditory feedback and reducing the need for manual adjustments.
McCormick also talks about creating a Slack summary Chrome extension that uses AI to automatically summarize external links, making it easier to process information without having to open each link individually. He details the development process, including the use of tools like Claude Code, VS Code, and symbolic links to manage configurations and streamline workflows. The focus is on how accessibility features, keyboard shortcuts, and consistent practice with AI can lead to better efficiency and less cognitive strain over time.
The podcast underscores the iterative and ongoing nature of McCormick's project, illustrating how personal software development, powered by AI, can be tailored to individual needs. It highlights the benefits of automating repetitive tasks to improve productivity and the potential of AI to create more inclusive and user-friendly digital experiences for people with disabilities.
22 Jun 2026 How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead
Recommended: AI finds bugs
Firefox employs AI agents as "coding archaeologists" to detect and address security vulnerabilities in its massive codebase, leveraging models like Mythos and custom validation tools to identify and systematically fix nearly 500 bugs, while balancing automation with human oversight and open-source collaboration to enhance scalability and security.
17 Jun 2026 How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex
Prompts and loops in AI automation are highlighted for their role in enabling structured task execution through clear automation design, sandboxed workflows, plugins, and subagents, with applications in software engineering and integration with tools like GitHub and Slack.
15 Jun 2026 How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal
AI integration in software engineering enables agents to handle complex tasks through benchmarking and optimization, shifts engineers toward higher-level work, and addresses challenges like reliability, data parsing, and balancing automation with human expertise while emphasizing outcome-focused systems over procedural methods.
9 Jun 2026 Claude Fable 5 review: what the new Mythos model gets right (and very wrong)
Anthropic's Claude Fable Five excels in long-term technical tasks with strong coding, vision, and async workflow capabilities but faces high token costs, design limitations, and restricted use in cybersecurity/biology, making it suitable for precise, extended projects rather than creative or agile workflows.
1 Jun 2026 Building an iPhone app with zero technical skills | Bryce Rattner Keithley
A non-technical developer created the *Daily Hundreds* iPhone app using AI tools like Replit and Gemini, blending personalized workouts with anthropomorphic animal demonstrations, overcoming technical hurdles through iterative testing and adaptive problem-solving.