Martian Chronicles

AI gathers review evidence better than any human, but lacks context. Here’s why human judgment still drives our final performance ratings.

Why multi-repo setups are vital for Claude Code, and their trade-offs.

We put the new Fable AI model to the test on a real production project: how we compressed two weeks of development into just five hours, and why true success still depends on solid architecture and human review.

A mysterious crash turned out to be Chrome's translator quietly rewriting the DOM behind React's back.

A non-technical PM's ground-level view of using Claude day to day: writing itself into status reports, explaining unfamiliar tools, sharpening QA, and drawing the line between understanding a system and building one.

We shipped llms.txt on marsbased.com and checked the data. Honest verdict: low cost, useful for docs, not a SEO play, and almost no bots read it yet.

AI gathers review evidence better than any human, but lacks context. Here’s why human judgment still drives our final performance ratings.

How MarsBased uses Claude and Linear to automate PM workflows, shifting the role from administrative tasks to strategic product thinking.

WebMCP is the new W3C standard that makes websites natively operable by AI agents, no slow vision models needed. Learn how to implement it in 15 minutes.