proomt

Search

Search posts, papers, and topics

All posts

Hacker News front pageGraafHenk2 min readrelease notesintermediate

WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages

Read on github.comHN 180·62 comments

Summary

Numberwang is a tiny character‑level CNN packaged as a 1.8 MB JSON model and a ~100‑line pure‑Python inference script that classifies numeric strings in eleven languages without any external dependencies. It reaches 88.9 % macro‑F1 on a held‑out set, but struggles with unseen arithmetic expressions.

  • The model is a 1.8 MB JSON file with ~100 lines of pure‑Python inference code, requiring no external libraries.
  • Architecture: character‑level CNN (Embedding→Conv1d→ReLU→global max pool→Linear→softmax) with 80 k parameters.
  • Achieves 88.9 % macro‑F1 on a 486‑sample test set; arithmetic on unseen operands is the weakest area (44–72% F1).
  • Supports eleven languages, digits, words, Roman numerals, arithmetic expressions, and various formats without tokenizers or rules.

Useful for engineers who need zero‑dependency, low‑footprint ML inference or multilingual number parsing.

6/10
machine learningpythonperformanceml inframultilingual

Related reading

  1. Scaling Telco Autonomy: Leveraging GNNs with Distributed GraphFlow

    Google Cloud’s blog introduces Distributed GraphFlow (DGF), an open‑source Python library for building and scaling Graph Neural Networks (GNNs) on a Spanner‑backed digital twin of telecom networks. The post outlines the three‑layer architecture (digital twin on Spanner Graph, ML layer with DGF, AI agents) and highlights DGF’s high‑level API (5‑line example) and low‑level primitives, but provides…

    Google Cloud Bloggoogle.com3 min

  2. Article: Your Next DSL Author Is a Language Model

    Typed Domain Grounding (TDG) embeds a DSL inside a mainstream language the LLM already knows (e.g., Kotlin) and uses the host compiler as an oracle. The author describes five building blocks—embedding, choosing a host language with high training‑data frequency, compiler‑driven type safety, a generate‑compile‑repair loop, and an on‑demand teaching tool—and shows measured results from kUML, a Kotli…

    InfoQinfoq.com18 min

  3. Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

    Feyospace‑v1 presents a data‑centric training pipeline for cyber‑security agents, combining five systems (Choulea, SkyReal, Hongzwang, PSBreakup, Kreator) to generate and verify 164 k long‑context trajectories across diverse exploit environments. The resulting checkpoints improve baseline performance by ~24% on CyberGym and achieve a 63% verified success rate, ranking top among similarly‑sized op…

    Hugging Face Daily Papersarxiv.org1 minpaper

  4. Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

    Zing‑0.5 is a 5 B autoregressive world model that lets users control generated environments in real time using both keyboard actions and text prompts. The paper introduces unified action‑text conditioning, segment‑level teacher distillation, and a low‑cost streaming inference pipeline that runs at 24 FPS (832×480) for about $0.009 per minute, achieving 81 % overall and 88.5 % consistency on a nav…

    Hugging Face Daily Papersarxiv.org1 minpaper

  6. Lies, Damn Lies and Benchmarks

    Codename One engineers dissect why benchmark numbers can be misleading, then share concrete work on GC tuning, proper weak/soft references, and a new probing sequence for their open‑addressed HashMap that cuts miss‑probe counts from >16 k to ~1.5 per lookup.

    CodeName Onecodenameone.com20 min