惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

MyScale Blog
MyScale Blog
F
Fortinet All Blogs
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
D
Docker
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
爱范儿
爱范儿
V
Visual Studio Blog
Last Week in AI
Last Week in AI
WordPress大学
WordPress大学
aimingoo的专栏
aimingoo的专栏
小众软件
小众软件
L
LangChain Blog
Vercel News
Vercel News
阮一峰的网络日志
阮一峰的网络日志
IT之家
IT之家
P
Proofpoint News Feed
博客园_首页
D
DataBreaches.Net
T
The Blog of Author Tim Ferriss
The GitHub Blog
The GitHub Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
C
Check Point Blog
Engineering at Meta
Engineering at Meta
Microsoft Azure Blog
Microsoft Azure Blog

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace
GitHub - kerv/laze
kerv · 2026-05-12 · via Hacker News - Newest: "LLM"

Laze — LLM-Authored Zero Effort

⚠️ Warning: This was just an experiment in which I asked Claude Opus 4.7 to create a programming language in the most efficient way it could. It isn't meant to be a serious thing — just a fun weekend project exploring what happens when you let an LLM design its own language.

📝 LinkedIn Post

Laze NES Emulator

A programming language optimized for LLM authoring that compiles to native macOS binaries. Indentation-based, minimal punctuation, infix operators.

Thoughts

Even though this isn't C code, the compiler does generate C internally as an intermediate step. This is an LLM — it specializes in text-based, readable input because that's what it's trained on. It's not going to emit raw bytecode or hand-tuned assembly efficiently. If you wanted a more efficient language, you shouldn't be using an LLM to write it. The point of Laze is to be the language that an LLM can produce the most correct, bug-free code in, as fast as possible. Minimal punctuation, no ambiguity, and direct access to system libraries.

Also... who in their right mind would make a single nes.laze file that is 2000+ lines of code... guess the AI will! I didn't ask it to split files, so maybe it needs some additional work.

Quick Start

python3 laze/lazec.py hello.laze hello
./hello

Example

extern _write
extern _exit

fn main()
  msg := "Hello, world!\n"
  write(1, msg, 14)
  exit(0)

Language Reference

Functions

fn name(param: type, param2: type) -> rettype
  body

Types: u8, u16, u32, u64, i8, i16, i32, i64, ptr

Variables

x := 42          ; declare + assign
x = x + 1        ; reassign

Control Flow

if condition
  body
end

if condition
  body
else
  body
end

while condition
  body
end

Operators

All standard infix: + - * / % & | ^ << >> == != < > <= >= && ||

Memory (byte arrays)

buf := malloc(1024)
buf[0] = 65          ; store byte
v := buf[0]          ; load byte

Directives

extern _funcname     ; declare external C function
link SDL2            ; link library
linkpath /opt/lib    ; add library search path
framework Cocoa      ; link macOS framework

Comments

Architecture

The compiler (laze/lazec.py) is a Python tool that:

  1. Parses .laze source into an AST
  2. Generates C internally (never written to disk)
  3. Pipes to cc -O2 for optimized native binary output

No .c files are created — code exists only in memory during compilation.

NES Emulator

A complete NES emulator written in Laze:

python3 laze/lazec.py nes.laze nes
./nes "Super Mario Bros. (World).nes"
./nes "Legend of Zelda, The (USA) (Rev 1).nes"

Requires SDL2 (brew install sdl2). Defaults to "Super Mario Bros. (World).nes" if no argument given.

Features

  • 6502 CPU (all official opcodes)
  • PPU with background, sprites (8x8 and 8x16), scrolling
  • APU with 2 square wave channels + triangle
  • Controller input
  • Mapper 0 (NROM), Mapper 1 (MMC1), Mapper 4 (MMC3)

Controls

  • Arrow keys: D-pad
  • Z: A button
  • X: B button
  • Return: Start
  • Right Shift: Select

Supported Games

  • Super Mario Bros. (Mapper 0) — fully playable
  • Legend of Zelda (Mapper 1) — playable with minor glitches
  • Super Mario Bros. 3 (Mapper 4) — experimental