8000 GitHub - eightman999/eightman999 ยท GitHub
[go: up one dir, main page]

Skip to content

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

ย 

History

25 Commits

Folders and files

NameName
Last commit message
Last commit date
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

header

๐Ÿ  eightman999

typing


๐Ÿง‘โ€๐Ÿ’ป About Me

I'm an information engineering student in Japan building local AI systems, LLM inference tools, coding-agent workflows, and apps.

My projects usually start with a question: Can this actually work? I enjoy testing ideas on everything from Apple Silicon to aging GPUs, then publishing implementations, measurements, and their limitations.

  • ๐Ÿง  Persistent/distributed cognition, memory, and AI agent architectures
  • โšก Local LLM inference, speculative decoding, and multi-GPU performance
  • โ™ป๏ธ Legacy-GPU software, OpenCL 1.1, and salvaged computing
  • ๐Ÿ‡ฏ๐Ÿ‡ต Japanese tokenizers, fiction-oriented language models, and long-context evaluation
  • ๐Ÿงช Reproducible benchmarks, regression tests, experiment records, and honest failure analysis
  • ๐Ÿ› ๏ธ macOS / Android / web apps, creative software, and developer tools

Languages: Rust ยท Python ยท Swift ยท Kotlin / Java ยท C / C++ ยท C# ยท TypeScript / JavaScript

ๆ—ฅๆœฌ่ชžใงใ‚‚ๆดปๅ‹•ใ—ใฆใ„ใพใ™ใ€‚**ใ€Œๅ‹•ใใจใ“ใ‚ใพใงไฝœใ‚Šใ€ๅฎŸๆธฌใ—ใ€ๅ†็พใงใใ‚‹ๅฝขใงๅ…ฌ้–‹ใ™ใ‚‹ใ€**ใ“ใจใ‚’ๅคงๅˆ‡ใซใ—ใฆใ„ใพใ™ใ€‚


๐Ÿ”ฌ Current Focus

October 2026 ยท public projects and experiments

Area Project / work
๐Ÿงฌ Kamimusuhi / ใ‹ใฟใ‚€ใ™ใณ Experimental architecture for a persistent artificial cognitive individual: continuity, provenance, memory, and delegation across models and machines.
โ™ป๏ธ SalvagedComputing / ScrapGpuLibrary Finding useful roles for obsolete GPUs and constrained machines. Working on legacy OpenCL 1.1 inference through CL11 and portable runtime components.
โšก Strata experiments / Qwen3.8 MTP Practical local inference with limited hardware: decoding speed, memory, quantization, and model/runtime tuning.
๐Ÿ“ YLSB / llama-split-bench Reproducible benchmarking of complete local-LLM configurations, including GPUs, split mode, context, KV cache, quality, and speed.
๐Ÿ‡ฏ๐Ÿ‡ต J-series Tokenizers v2 / novllm Japanese tokenizer design and model training/evaluation for long-form and fiction generation, with public research tooling.
๐Ÿค– rustdsh / rdsh Contributing to Rust tooling for AI coding agents: provider integrations, execution workflows, developer experience, and safety.
๐Ÿฝ๏ธ OISINT An evidence-backed restaurant research and comparison app, including source links, uncertainty, and collaborative decisions.

Additional experiments: NavSpec (structured naval-spec generation and validation) and Open Jev Core ML (experimental Apple Silicon inference, with documented limitations).

๐Ÿค Community & Open Source

I founded and help run the ๅœฐๅ…ƒใฎLLM community on local-AI tooling, including ScrapGpuLibrary, rustdsh, and the community Bench of Us reports.

I also contribute to J-LLM on Hugging Face, sharing Japanese models, tokenizers, and other experimental artifacts. The J-series v2 collection covers multiple tokenizer vocabulary sizes.

Projects vary in maturity. A prototype, a benchmark, or a successful test is not a production guarantee.


๐Ÿš€ Selected Software

  • ๐ŸŒธ Ourin / ๆกœ้ˆด โ€” macOS-native Ukagaka-compatible baseware, built with Swift and native SHIORI runtimes.
  • ๐Ÿ” DiffLoupe โ€” a macOS-native folder/file diff tool inspired by WinMerge.
  • โœ’๏ธ Singleline JP Font โ€” Japanese centerline fonts and 1-bit assets; the expanded v2 family is still a release candidate with proofreading in progress.
  • โš“ NavSpec โ€” structured fictional 9089 naval specification generation, constraints, and regression evaluation.
  • ๐Ÿง  Open Jev Core ML โ€” experimental Core ML / Apple Silicon conversion and benchmark results, including negative findings.
  • ๐Ÿ› ๏ธ HOI4 Modding AI Agent Skills โ€” reusable references and agent skills for game modding.
  • ๐Ÿ“ฑ WattTime โ€” a published Android microwave heating-time converter built with Kotlin.

See more in my repositories and on Furin Lab.


๐Ÿงญ How I Work

idea / problem
    โ†“
survey & design
    โ†“
prototype
    โ†“
measurement / benchmark
    โ†“
failure analysis
    โ†“
reproducible artifact
    โ†“
next experiment

I use AI coding agents heavily, but try to keep claims separate from measurements: CI, test results, raw outputs, hashes, experiment manifests, and failure records matter more than "it seems to work".

I also run local experiments across Apple Silicon, CUDA, and legacy OpenCL systems, including mixed-generation NVIDIA GPUs, so hardware constraints are treated as part of the research rather than an afterthought.


๐Ÿ’ป Tech & Research Stack

Languages

Languages

Development / ML

Development and ML

PyTorch ยท Transformers ยท MLX / MPS ยท llama.cpp / ggml ยท CUDA ยท OpenCL ยท Core ML ยท Metal

GitHub Actions ยท SQLite ยท Supabase ยท Cloudflare

AI-assisted development

ChatGPT Claude Gemini Codex

๐Ÿ”— Links

๐Ÿ  Personal site eightman999.com โ€” works and notes
๐ŸŽ Furin Lab furinlab.com โ€” apps and public releases
๐Ÿค— Hugging Face Furinlab ยท J-LLM
๐Ÿ‡ฏ๐Ÿ‡ต Japanese tokenizers J-series v2 collection
๐Ÿค Local LLM community jimoto-no-llm ยท Bench of Us
๐Ÿฝ๏ธ OISINT oisint.com
๐Ÿฆ X @eightman999
๐Ÿ’ฌ Discord _eightman_
๐Ÿณ Off-keyboard Cooking and eating good food

๐Ÿ“Š GitHub Analytics



๐Ÿ’ฌ ๅŠ›ใฏใ€Œๅ‡บใ‚‹ใ‚‚ใฎๅ‡บใ›ใ‚‹ใ‚‚ใฎใ€
๐Ÿ’ฌ ใ€Œใ‚„ใฃใฆใฟใ‚ˆใ†ใ€ใจใ€Œใฉใ†ใ›้ง„็›ฎใ ใ€
โ€” ็พฝไปใ‚‚ใจๅญใ€Ž็พฝไปใ‚‚ใจๅญ่‘—ไฝœ้›†ใ€

footer

ยฉ 2026 eightman999 ยท Furin Lab ยท build, measure, iterate.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

0