Simon Willison shares highlights from his appearance on Lenny's Podcast, covering the state of AI-assisted software development. Key themes include a November 2025 inflection point where GPT and Claude models crossed a threshold of reliability for coding agents, the mental exhaustion of running multiple agents in parallel, how
Table of contents
Highlights from my conversation about agentic engineering on Lenny’s PodcastThe November inflection point #Software engineers as bellwethers for other information workers #Writing code on my phone #Responsible vibe coding #Dark Factories and StrongDM #The bottleneck has moved to testing #This stuff is exhausting #Interruptions cost a lot less now #My ability to estimate software is broken #It’s tough for people in the middle #It’s harder to evaluate software #The misconception that AI tools are easy #Coding agents are useful for security research now #OpenClaw #Journalists are good at dealing with unreliable sources #The pelican benchmark #And finally, some good news about parrots #YouTube chapters #Sort: