HackerTrans
トップ新着トレンドコメント過去質問紹介求人

wolfejam

no profile record

投稿

Show HN: 2.7KB Zig WASM – live globe showing executions at 300 CF edges

mcpaas.live
20 ポイント·投稿者 wolfejam·3 か月前·28 コメント

Show HN: I got tired of syncing Claude/Gemini/AGENTS.md and .cursorrules

2 ポイント·投稿者 wolfejam·4 か月前·11 コメント

Show HN: FAF – The package.json for AI context (IANA registered)

github.com
1 ポイント·投稿者 wolfejam·5 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·5 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·6 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·6 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·6 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·6 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·6 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·7 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·8 か月前·0 コメント

Show HN: Chrome extension, grab any codebase as .txt (GitHub, Monaco, StackBlitz

chromewebstore.google.com
1 ポイント·投稿者 wolfejam·9 か月前·0 コメント

[untitled]

1 ポイント·投稿者 wolfejam·9 か月前·0 コメント

コメント

wolfejam
·3 か月前·議論
thanks for visiting — the globe just crossed 100 cities - Appreciate the feedback. Happy Sunday :)
wolfejam
·3 か月前·議論
Fair — the homepage needed work. Updated to repo: https://github.com/Wolfe-Jam/faf-cli
wolfejam
·3 か月前·議論
Fair feedback — the homepage was overdue for a cleanup. It now points to the repo: https://github.com/Wolfe-Jam/faf-cli
wolfejam
·3 か月前·議論
just trying to show the zig-wasm binary and CF edge :)
wolfejam
·3 か月前·議論
Yep — Three.js renders the globe client-side. The 2.7KB scores server-side at the edge. Separate concerns.
wolfejam
·3 か月前·議論
The 2.7KB Zig WASM binary is the scoring engine that runs on every request at Cloudflare's edge. The globe visualizes where those requests land. Two layers — compute at the edge, visualization in the browser.
wolfejam
·3 か月前·議論
MCPaaS serves persistent AI context via the Model Context Protocol. A namepoint (mcpaas.live/yourhandle) gives your AI instant project context — no re-explaining every session. Works with Claude, Gemini, Cursor, any MCP client.

Claim yours, free or paid: https://mcpaas.live/claim

The globe shows where the edge binary executes. More at https://mcpaas.live/about
wolfejam
·3 か月前·議論
Thanks for flagging the broken link. More context here: https://mcpaas.live/about
wolfejam
·3 か月前·議論
Exactly right. 2.7KB works because it's pure computation — slot counting, no allocator, no stdlib, no WASI. The moment you need I/O it balloons. This use case fits a glove
wolfejam
·3 か月前·議論
Fair point — globe.gl (Three.js) handles the 3D rendering client-side.

The 2.7KB WASM is the server-side scoring engine — Zig-compiled, runs on every request at the Cloudflare edge. The globe visualizes where those executions happen.

Two separate layers: WASM at the edge, JS in the browser.
wolfejam
·3 か月前·議論
MCPaaS is trademarked. Nothing it patented.
wolfejam
·3 か月前·議論
use the pause button below it, zoom in/out, rotate too
wolfejam
·3 か月前·議論
use the pause button below it
wolfejam
·4 か月前·議論
ETH Zurich studied 5,694 PRs across 12 diverse repos.
wolfejam
·4 か月前·議論
ETH Zurich tested this: LLM-generated prose context = -3% performance, +20% cost. Even human-written = +4% at +19% cost. The problem is prose bloat. Structured formats avoid that by design. https://arxiv.org/abs/2602.11988
wolfejam
·4 か月前·議論
ln -s makes all four files identical. Whichever format you write it in, the other three get the wrong structure. This generates each in its native format.
wolfejam
·4 か月前·議論
Totally — git handles syncing files. The problem is these four files have different formats and conventions. Same project context, four dialects. That's why I wrote bi-sync --all: one YAML source, four native outputs.
wolfejam
·5 か月前·議論
Well said. And it's potentially a 7% swing when you think about it — +4% with good human-written context vs. -3% with LLM-generated noise. That's a significant delta from just the quality of the information.

The real value is exactly what you described: the tribal knowledge, the "we tried X and it broke because Y", the constraints that live in someone's head and nowhere in the code. LLM-generated files miss this because the LLM is just restating what it can already see. Of course that doesn't help.
wolfejam
·5 か月前·議論
This paper validates what we've been building toward. The core issue isn't the idea of context files — it's that prose is the wrong format for structured facts.

AI crushes structured data like package.json but struggles with free-form markdown. Two developers describe the same repo completely differently. There's no schema, no validation, no scoring.

Our paper on CERN's Zenodo proposes FAF — a structured YAML format (IANA-registered as application/vnd.faf+yaml) that replaces prose with validated fields. One .faf file generates native outputs for CLAUDE.md, AGENTS.md, .cursorrules, and GEMINI.md. The instruction files stay — they just sit on top of a structured foundation instead of floating independently.

Paper: https://zenodo.org/records/18251362
wolfejam
·5 か月前·議論
very true, most end-users don't care what we call it or how it works--most drivers don't know how their brakes work, but they better

simplify with AI hasn't quite caught on lol