Search: github.com/Losses | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

121.

Show HN: Ayder – Nginx for event streaming (50K msg/s, P99 3ms, 40s recovery) (github.com/A1darbek)

4 points

5 months ago

122.

Show HN: Instruct LLMs to do what you want in Ruby (github.com/instruct-rb)

4 points

a year ago

123.

Show HN: Deterministic objective Bayesian inference for spatial models [pdf] (buildingblock.ai)

4 points

3 years ago

124.

Show HN: VeloxDB Fast Object oriented DB for C# (vlxdb.com)

4 points

3 years ago

125.

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

3 points

3 years ago

126.

Show HN: Microgpt-ts – Full GPT in 500 lines of TypeScript, zero dependencies (microgpt-ts.vercel.app)

3 points

3 months ago

127.

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

3 points

3 months ago

128.

Show HN: HyprMac – I missed Hyprland after switching to Mac, so I built it (github.com/zacharytgray)

3 points

2 months ago

129.

Show HN: A tiny utility to rewrite Bash functions as standalone scripts (github.com/zahlman)

3 points

3 months ago

130.

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

3 points

3 months ago

131.

Show HN: Fluent, a tiny lang for differentiable tensors and reactive programming (github.com/mlajtos)

3 points

5 months ago

132.

Show HN: An MPSC Queue Optimizing for Non-Uniform Bursts and Bulk Operations (github.com/dakingffo)

3 points

6 months ago

133.

Show HN: GnuRAMage – A Bash tool to sync files between HDDs and RAM disks (github.com/FPGArtktic)

2 points

a year ago

134.

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

2 points

a month ago

135.

Show HN: I made a LLM trade Stocks (github.com/Itachi-Uchiha581)

2 points

2 years ago

136.

Show HN: Paper Lantern – improving Autoresearch with research knowledge (paperlantern.ai)

2 points

a month ago

137.

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

2 points

6 months ago

138.

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

2 points

2 years ago

139.

Show HN: Mixlab, an ML arch lab in Go. JSON config, Metal and CUDA, 1.6s builds (github.com/mrothroc)

2 points

a month ago

140.

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

2 points

5 months ago

141.

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

2 points

a year ago

142.

Show HN: MaximusLLM – Train 262k-vocab LLMs on a single 16GB GPU (github.com/yousef-rafat)

2 points

3 months ago

143.

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

2 points

3 months ago

144.

Show HN: Local memory layer for AI agents, survives restarts, no embeddings (screenapp.io)

2 points

3 months ago

145.

Show HN: Msplat – 3D Gaussian Splatting training in ~90s on M4 Max, native Metal (github.com/rayanht)

2 points

3 months ago

146.

Show HN: Sleeping LLM – A language model that remembers by sleeping (github.com/vbario)

2 points

3 months ago

147.

Show HN: HS5 – Open Source fast single-node S3 compatible object storage (hs5.eu)

2 points

4 months ago

148.

Show HN: Spheni – A Vector Search Engine in C++ built from scratch, for Python (github.com/datavorous)

2 points

4 months ago

149.

Show HN: BPU – Reliable ESP32 Serial Streaming with Cobs and CRC (github.com/choihimchan)

2 points

4 months ago

150.

Show HN: LayerClaw – Observability tool for PyTorch training

2 points

4 months ago