lennysnewsletter.com

🎙️ How I AI: 8 real Jev use cases + How OpenAI uses ChatGPT Sites (live at DevDay!) + Claire’s DevDay recap

Software can now be temporary and still worth building. Kath might create a personalized site for one business trip, use it for a week, and discard it afterward. When development overhead falls far enough, even a tool with a seven-day lifespan can deliver meaningful value.

lennysnewsletter.com

I tested Grok Bot, Grok 4.6, and Cursor Origin - here’s my honest take

I set up five Grok Bots, ran Grok 4.6 through my Claire Weighted Index against GPT-5.6 Sol, Claude Sonnet 5, and Opus 5, and spent time actually using Origin as a GitHub replacement. Here's what's worth your attention, what's overhyped, and where I'm personally putting my time.

lennysnewsletter.com

🎙️ How I AI: GPT-5.6 review, How a solo builder runs 24/7 local AI, and What an agent harness is and how to build one

The open chat field has been good enough, until it stopped being good enough. I acknowledge in this episode that just typing into Claude Code has produced real work. But this marks a shift in my thinking: general-purpose agents are now better used to orchestrate specialized harnesses than to do every job themselves. Giving a constrained agent a specific harness gets more consistent output than giving a powerful agent an open prompt.

platformer.news

Vibe coding has escaped the terminal

Until recently, software development was too expensive to pursue something so stupid. Not anymore!

noahpinion.blog

How much more software do we really need?

For companies using advanced AI coding tools, only 18% of spending on tokens is translating into shipped coding products that reach real users, according to EntelligenceAI, a startup that aggregated data on more than 2,000 companies using advanced AI tools for coding. Jellyfish, a company that tracks AI usage, found rapidly diminishing returns in terms of converting tokens to actual software.