This explains how to use a “premortem” prompt with AI—telling it your plan already failed six months later—to force it to list failure scenarios and warning signs. It then ranks the most likely and dangerous failures, reveals hidden assumptions, and suggests plan adjustments.

• Asking AI "is this plan solid?" produces biased cheerleading because it's trained to be affirming, not critical
• The fix is a "premortem" prompt: telling the AI the plan already failed six months from now and asking it to explain why, which surfaces failure scenarios and early warning signs
• Kahneman considers premortems his top decision-making tool, and companies like Google, Goldman Sachs, and P&G use them before major launches
• A follow-up synthesis step has the AI rank the most likely failures, name the biggest hidden assumption, and rewrite the plan to close those gaps

This article discusses the dangers of accumulating technical debt, especially in the context of rapid AI advancements. While it may seem beneficial to defer debt repayment for future improvements, this approach can lead to an overwhelming complexity that even AI tools can't manage. Developers must balance short-term gains with long-term sustainability.

• AI-assisted coding tempts developers to defer technical debt indefinitely, betting that future model improvements will make it cheap to fix later, with some codebases growing past 40,000 lines/day.
• This bet assumes AI capability growth continues indefinitely, but once it plateaus, accumulated debt becomes unfixable by any human or AI.
• The result is "subprime" technical debt—debt whose risk was mispriced on the assumption of endless future gains, setting up an eventual reckoning.