Published 27 Jan 2026
Duration: 2424
Software development experts discuss the importance of general-purpose AI agents, scalable solutions, and simplicity in design, with a focus on expanding AI capabilities beyond coding to tackle broader software engineering challenges.
If you rely on complex scaffolding to build AI agents you aren't scaling you are coping. Thibault Sottiaux from OpenAIs Codex team joins us to explain...
The podcast explores the transformation of OpenAI's Codex into a general-purpose AI agent designed to adapt across various software development scenarios. It emphasizes the value of building scalable, foundational systems over focusing on specific products, reflecting the "bitter lesson" in AI that scalable solutions tend to prevail over domain-specific optimizations. The discussion advocates for simplicity in design to avoid unnecessary complexity and outlines a vision for the agent to evolve beyond coding into broader software engineering tasks.
Looking ahead, the team aims to develop multi-agent networks that could significantly enhance productivity. Open-sourcing the agents repository is seen as a way to encourage innovation and collaboration within the community. Insights from earlier open-source efforts and language transitions, such as moving from TypeScript to Rust, underscore the importance of adaptability and user feedback. Future challenges include improving the agent's efficiency in long-running tasks and tailoring its behavior to better match individual user preferences and workflows.
31 Mar 2026 Retrofit or reimagine? Developer environments for humans and agents | Onas Matt Boyle
Agentic AI platforms prioritize secure, ephemeral enterprise workspaces with pre-configured environments, emphasizing Onas' optimized workflows, security measures like kernel-level controls, and future integration with project management systems to enhance productivity and scalability.
27 Mar 2026 The T-shaped leader, Disney cant catch a break, and will you trust Auto mode?
Rising AI costs, OpenAI's shift to enterprise strategies, video AI's practical limitations, safety concerns, evolving software roles, corporate lock-in tactics, and calls for robust frameworks and safeguards underscore AI's uneven adoption and challenges in responsible development.
24 Mar 2026 Why AI-assisted PRs merge at half the rate of human code | LinearBs 2026 Benchmarks
The 2026 Engineering Benchmark Report reveals that while 88.3% of developers use AI regularly, AI-generated pull requests face low merge rates (32.7%), larger sizes, and prolonged reviews due to systemic issues like poor data quality, inadequate policies, and organizational gaps, emphasizing the need for governance, smaller focused PRs, and foundational practices to optimize AI's potential in engineering workflows.
20 Mar 2026 Sloppypasta culprits, unpacking MCPs spotlight, and Anthropic wants your agents to work the graveyard shift
Strategies for optimizing AI token usage, critiques of MCPs, context anchoring for memory degradation, debates on ephemeral vs. cumulative workflows, decentralized web practices, AI content misattribution, Apex framework for productivity impact, and a potential digital Renaissance via low-cost tools and AI integration.
17 Mar 2026 Many tokens make all bugs shallow & open sources new maintainers | Chainguard's Dan Lorenc
AI is reshaping engineering by accelerating development through code generation but introduces security risks, infrastructure challenges, and supply chain vulnerabilities, demanding human oversight, robust safety protocols, and balanced innovation with adaptability, education, and cultural security prioritization.