{"version":1,"type":"story","url":"https://digestai.news/story/krlntn-builds-neural-network-that-boots-pc-from-512byte-mbr","json":"https://digestai.news/story/krlntn-builds-neural-network-that-boots-pc-from-512byte-mbr.json","markdown":"https://digestai.news/story/krlntn-builds-neural-network-that-boots-pc-from-512byte-mbr.md","slug":"krlntn-builds-neural-network-that-boots-pc-from-512byte-mbr","headline":"Krlntn builds neural network that boots PC from 512‑byte MBR","summary":"The project is a neural network that runs in 16‑bit real mode on a 386, loaded from a 512‑byte MBR. The author, krlntn, writes hand‑crafted assembly that loads an 11.5‑KB int8 model from the next 23 sectors. The model is a single‑hidden‑layer char‑level net trained on fake dmesg logs. The boot sector prints a simulated Linux boot log, including timestamps, PCI bars, ACPI events, and a command line. The code uses int 13h to load weights, int 10h to print, and integer math for activation and sampling.\n\nThe author provides scripts: corpusgen.py creates 3 MB of fake logs, train.py trains and quantizes the model, boot.asm contains the runtime, and record.py captures a demo GIF from QEMU. The project references earlier boot‑sector AI demos such as sectorllm, sectorlisp‑nn, and bootgpt, and cites Oscar Toledo’s 512‑byte games. The demonstration shows that a tiny neural net can run on bare hardware without an OS, highlighting the limits of inference on constrained devices.","keyPoints":["krlntn loads an 11.5‑KB int8 model from 23 sectors and runs it in 16‑bit real mode on a 386.","The boot sector prints a simulated Linux boot log with timestamps, PCI bars, ACPI events, and a command line.","Scripts include corpusgen.py for fake logs, train.py for training, boot.asm for runtime, and record.py to capture a demo GIF from QEMU."],"whyItMatters":"The demo shows that a tiny neural net can run on bare hardware without an OS, illustrating the limits of inference on constrained devices and inspiring new low‑power AI applications.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":[],"models":[],"people":["krlntn","Oscar Toledo"]},"firstPublishedAt":"2026-10-31T12:58:29Z","updatedAt":"2026-10-31T12:58:29Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"github.com","title":"Show HN: A language model that lives in a boot sector","url":"https://github.com/kerlenton/bootgpt","publishedAt":"2026-10-31T12:58:29Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[{"site":"Hacker News","url":"https://news.ycombinator.com/item?id=50315782","points":43}],"thread":null,"cite":{"text":"Digest AI, \"Krlntn builds neural network that boots PC from 512‑byte MBR\", 31 October 2026, https://digestai.news/story/krlntn-builds-neural-network-that-boots-pc-from-512byte-mbr","publisher":"Digest AI","title":"Krlntn builds neural network that boots PC from 512‑byte MBR","datePublished":"2026-10-31T12:58:29Z","url":"https://digestai.news/story/krlntn-builds-neural-network-that-boots-pc-from-512byte-mbr"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}