Duly Noted

Large language models are trained to continue patterns in ways that sound right to humans. They are optimized to produce answers, not to stop and say “I don’t know.” That incentive structure matters. When a model fills gaps, it does so confidently, because confidence reads as usefulness. Treat AI output as a proposal, not an answer.

Ai isn’t going to have to answer the page after hours. And it will always add more code when removing might be the answer.

_{Quote Citation: https://hashnode.com/@voidrane, “Why AI Makes Bad Systems More Convincing”, 2025-12-14, https://chaincoder.hashnode.dev/why-ai-makes-bad-systems-more-convincing}