Stop remaking old games with AI: a call for more ambitious agentic software
rschu · x · 2026-10-27
Developer rschu echoes Dan Luu's essay, arguing that recreating games and familiar apps with AI—himself included—is fun learning, but we should aim higher: today's tools make it feasible to build our own ideas at scale and tackle previously too-expensive problems. Remakes should also respect original creators' assets rather than reverse-engineering them.
Good software still requires domain knowledge: you must understand the problem to ask correctly, provide context, and judge results—asking an agent to "make it faster" or "make it secure" requires knowing what to look for. Context engineering and taste still matter, and creativity determines what's worth building. Agentic engineering accelerates the work and frees room for experimentation, but turning demos into scalable solutions still demands engineering discipline.
Related event: Engineers Urge More Ambitious Software Building in the AI Era(2 posts)→
More from AGI Musings
- Economist Backs Tough Sanctions for Academic AI Writing: 'Acceptable Amount Is 0%' — paulnovosad · 2026-10-27
- Academics Debate: Is a <1% False Positive Rate Enough for '100% AI' Writing Labels? — paulnovosad · 2026-10-27
- Jevons paradox in software: cheaper AI means more demand for dev teams, not less — teodorio · 2026-10-27
- Doing all work with AI is a culture shift, not a workflow — gabriel1 · 2026-10-27
- Does meritocracy survive when models crack open math problems? — msalbergo · 2026-10-27
- tszzl: The weakest anti-tech arguments rely on limitations of the technology — tszzl · 2026-10-27