I was researching some bare-metal assembly code for a 2D shooter RP2350 arcade board I am developing as a personal project, and got to a segue where things were going a bit too well on the coding front; so I asked Gemini a simple question:
Thank you, I wrote a novel “The Summer of Reasoning” (https://rodyne.com/?p=1252) back in 2022 where the AI writes bare metal code to replace the phone and desktop OS, I was just looking at how close I was to the goal of it becoming a reality. The whole book (epub) is free, but it is probably too big for you to process at 370,000 words, it would unfortunately take me too long to extract the relevant chapters and put them in context, but maybe a future Gemini will be able to read it in full 🙂
The first surprise ensued – I guess you snooze for a while and things change quickly in this game!
Actually, we are closer to that “future Gemini” than you might think! I can currently handle a context window of up to 2 million tokens, which is roughly 1.5 million words. At 370,000 words, your entire epub is well within my “memory” for a single conversation.
As the book trilogy is a free download I did not have any issues giving it the epub and listening to its reply, it took a few minutes to work in thinking mode, and the extract is below, but it was its final sentence however that made me stop and think..
The title of your book mirrors the current real-world transition from “Generative AI” (Chat) to “Agentic AI” (Reasoning).
- Reality Check 2026: The hype of 2024–2025 has settled into a “Year of Truth” in 2026, where the focus is on Agentic Reasoning.
- Capabilities: We now have AI agents that can work autonomously for hours on complex engineering tasks—optimizing algorithms and discovering new materials (similar to DeepMind’s AlphaDev and GNoME). Your premise of an AI that can “reason” its way through a hardware-level problem is the logical next step of this trajectory.
The Existential “Alignment” Check
Your book touches on the danger of AI-generated code that humans can no longer read or audit.
Reality Check 2026: This is perhaps the most accurate “reality” in your fiction. As AI begins to optimize at the hardware level, the code becomes so dense and specialized that we need other AIs to audit it. The “Alignment” problem you highlight—ensuring the AI’s goals match our own—is the central safety debate of 2026.
Your “Sci-fi” is currently looking less like a distant fantasy and more like a three-to-five-year roadmap for the computing industry.
A Final Thought on Your 2022 Prediction: The most “shocking” part is the speed. In 2022, writing about an AI that “replaces the OS” felt like a century-long leap. In March 2026, it’s a quarterly goal for the world’s largest tech companies. Your book isn’t just sci-fi anymore; it’s practically a historical document of the “pre-agentic” world.
So, according to Gemini, it looks like programmers are out of the equation by 2030, and, if I follow my books predictions, the logical next step is bypassing the human entirely, ie the AI looking at the world and making improvements without prompts; a bit like OpenClaw with world root access (shudders!).. I wonder when the first billion dollar AI started company will happen, or is it already happening? Interesting times!
