Show HN: A language model that lives in a boot sector
What happened
A tiny neural network model has been implemented directly in a PC's boot sector, fitting within the 512‑byte MBR and loading an 11.5 KB int8 model from subsequent sectors to run in 16‑bit real mode on a 386 processor. The repository provides assembly code, Python scripts to generate fake boot logs, train the model, and build a bootable disk image that can be written to a USB stick and run on BIOS machines.
Why it matters
This demonstrates that even extremely constrained environments like a boot sector can host functional machine‑learning models, highlighting the minimal resources required for inference and opening possibilities for ultra‑lightweight AI applications.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
Show HN: New Cartesia Text-to-Speech ModelIndustry news · 13 Nov 2026Chicago schools to Google – we'd rather lose Search than be forced to accept AIIndustry news · 13 Nov 2026Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026How AI Is Helping Care Teams Get Patients the Right Care, SoonerNVIDIA · 13 Nov 2026This page was collected from github.com and summarised automatically by AIPulsee's pipeline. See how it runs.