This is the moment where the AI bot started showing its limitations, as it suggested changes to the circuit, blissfully unaware of the material or time costs involved. Ikejima rolled up his sleeves and got out his logic analyzer, which promptly "went berserk" on connection. As it turns out, the 8086 design uses the same physical line for addresses and code, switching between them at each clock tick.
Once he sorted that out with the control software, he came across another bug that should have been obvious: 8086 chips use one RAM chip for even bytes, and another for odd bytes. After a handful of fixes, Ikejima finally got the CPU to work and execute code. He then figured he wanted to run actual software on it, and settled on getting MS-DOS' COMMAND.COM.
That effort proved more than he had considered, as COMMAND.COM rewrites itself in memory, and requires some interfacing to an actual BIOS and I/O — while all he effectively had was a CPU socket and some memory. After more research, he settled on using HI-DOS on the cradle side to be able to have a BIOS, and eventually booted HIDOS MS-DOS, albeit with some limitations, like the lack of writeable storage and the limited amount of memory.
Even still, he did manage to run some simple programs, culminating in what's effectively a pretty impressive demonstration of what's possible when you couple human logic and reasoning with the massive helping hand of an AI bot. Do read the entire adventure at Ikejiima's blog .
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Bruno Ferreira is a contributing writer for Tom's Hardware. He has decades of experience with PC hardware and assorted sundries, alongside a career as a developer. He's obsessed with detail and has a tendency to ramble on the topics he loves. When not doing that, he's usually playing games, or at live music shows and festivals. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-16/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Bruno Ferreira Contributor Bruno Ferreira is a contributing writer for Tom's Hardware. He has decades of experience with PC hardware and assorted sundries, alongside a career as a developer. He's obsessed with detail and has a tendency to ramble on the topics he loves. When not doing that, he's usually playing games, or at live music shows and festivals.
hwertz Just to point out the 8086 came out in 1978 and the IBM PC in 1982. So I'm not sure where the 1987 date in the article came from. But good article, interesting to see someone have a go at this. Reply
damneardone It would have been informative to know what model of Gemini was used. Last years free models of Gemini compare to todays paid models like a Nissan Versa does to a Nissan GT-R. I mean, they're both Gemini/Nissan, but that's leaving a lot unsaid, when discussing performance. Besides, do we really want models that no longer need a human in the loop? Reply
roboj1m In using Gemini in the same way, I have human intuition and problem solving, it has speed and total recall of every microchip spec sheet, every purpose it's used for, every engineering discipline and when to use it, etc etc. The biggest thing, the bit that saves me the most time and effort, is knowing what to learn when there's almost infinite knowledge to learn. "I want to connect this FPGA hacking board to this data-bus and USB" "Well you'll need to know, this, that, the other thing and without a doohickey it'll catch on fire" "What if I do this instead?" "I didn't think of that, that solves the fire problem and also protects your XYZ55b" Without it, I don't know the technical terms. Without the technical terms you can't drive a search engine, it becomes a contextual, semantic search engine with the AI. And I remember hunting through microfiche readers in libraries. Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/raspberry-pi/raspberry-pi-projects/SPONSORED_LINK_URL
- https://www.tomshardware.com/raspberry-pi/raspberry-pi-projects/tech-tinkerer-gets-gemini-to-help-him-design-an-x86-motherboard-from-scratch-bot-help-was-impressive-but-project-still-required-human-awareness-and-intervention#main
- https://www.tomshardware.com
- Over 80% of companies report no productivity gains from AI so far despite billions in investment, survey suggests — 6,000 executives also reveal 1/3 of leaders
- IBM triples entry-level hires for 2026 despite AI adoption, bucking industry trends — Chief HR officer says that AI can do most entry-level jobs, but work still
- NZXT unveils new H2 mini PC with 9800X3D, Intel 285K configurations — H2 Flow Mini-ITX case and C850 SFX power supply for builders
- LaserPecker LX2 review: Large scale dual laser cutter
- This Corsair RAM and Gigabyte AM5 motherboard bundle is just $67 more than buying the RAM alone – 32GB of RAM and B850 Aorus Elite Wifi 7 shaves $133 off buying
Informational only. No financial advice. Do your own research.