Search: github.com/Losses | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

121.

Show HN: Rriftt_ai.h – A bare-metal, dependency-free C23 tensor engine

github.com/Rriftt

4 months ago

4 points

122.

Show HN: SGR – A Linear-Complexity "Living Cell" Outperforming Transformers

5 months ago

4 points

123.

Show HN: Ayder – Nginx for event streaming (50K msg/s, P99 3ms, 40s recovery)

github.com/A1darbek

6 months ago

4 points

124.

Show HN: Instruct LLMs to do what you want in Ruby

github.com/instruct-rb

2 years ago

4 points

125.

Show HN: Deterministic objective Bayesian inference for spatial models [pdf]

buildingblock.ai

3 years ago

4 points

126.

Show HN: VeloxDB Fast Object oriented DB for C#

3 years ago

4 points

127.

Ask HN: Legal question – liability for printed card deck of computer pranks

3 years ago

3 points

128.

Show HN: Microgpt-ts – Full GPT in 500 lines of TypeScript, zero dependencies

microgpt-ts.vercel.app

4 months ago

3 points

129.

Risk Management and Hedging in a Polymarket Dual-Side Arbitrage Bot

3 months ago

3 points

130.

Show HN: HyprMac – I missed Hyprland after switching to Mac, so I built it

github.com/zacharytgray

3 months ago

3 points

131.

Show HN: A tiny utility to rewrite Bash functions as standalone scripts

github.com/zahlman

4 months ago

3 points

132.

I built an AI browser with prompt-injection defense at 16 on an i5 with 8GB RAM

4 months ago

3 points

133.

Show HN: Fluent, a tiny lang for differentiable tensors and reactive programming

github.com/mlajtos

5 months ago

3 points

134.

Show HN: An MPSC Queue Optimizing for Non-Uniform Bursts and Bulk Operations

github.com/dakingffo

6 months ago

3 points

135.

Show HN: GnuRAMage – A Bash tool to sync files between HDDs and RAM disks

github.com/FPGArtktic

a year ago

2 points

136.

Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs

2 months ago

2 points

137.

Show HN: I made a LLM trade Stocks

github.com/Itachi-Uchiha581

2 years ago

2 points

138.

Show HN: Paper Lantern – improving Autoresearch with research knowledge

paperlantern.ai

2 months ago

2 points

139.

I built an open-weights memory system that reaches 80.1% on the LoCoMo benchmark

7 months ago

2 points

140.

Ask HN: How LLMs Learn to Be "Generative"?

2 years ago

2 points

141.

Show HN: Mixlab, an ML arch lab in Go. JSON config, Metal and CUDA, 1.6s builds

github.com/mrothroc

2 months ago

2 points

142.

Show HN: Lore – A reasoning engine that stores the "why" behind code changes

5 months ago

2 points

143.

Show HN: Loft CLI – Fine-tune and run LLMs (1–3B) on 8 GB MacBook Air, no GPUs

a year ago

2 points

144.

Show HN: MaximusLLM – Train 262k-vocab LLMs on a single 16GB GPU

github.com/yousef-rafat

3 months ago

2 points

145.

Show HN: Dspx – Native C++ DSP Library for Node.js Built for AWS Lambda (1.3MB)

3 months ago

2 points

146.

Show HN: Local memory layer for AI agents, survives restarts, no embeddings

3 months ago

2 points

147.

Show HN: Msplat – 3D Gaussian Splatting training in ~90s on M4 Max, native Metal

github.com/rayanht

4 months ago

2 points

148.

Show HN: Sleeping LLM – A language model that remembers by sleeping

github.com/vbario

4 months ago

2 points

149.

Show HN: HS5 – Open Source fast single-node S3 compatible object storage

4 months ago

2 points

150.

Show HN: Spheni – A Vector Search Engine in C++ built from scratch, for Python

github.com/datavorous

4 months ago

2 points