Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
331.
▲
Show HN: GnuRAMage – A Bash tool to sync files between HDDs and RAM disks
(github.com/FPGArtktic)
2 points
mokulanis
a year ago
6 comments
332.
▲
Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs
2 points
dnosoz
a month ago
4 comments
333.
▲
Show HN: FSP2 Tested on excerpt "Romeo and Juliet" impressive compresion results
2 points
Forgret
9 months ago
4 comments
334.
▲
Show HN: I made a LLM trade Stocks
(github.com/Itachi-Uchiha581)
2 points
Adeeb0123
2 years ago
3 comments
335.
▲
Show HN: Bytery – a binary JSON protocol ~10x faster and ~10x smaller
(github.com/jacksonsolid)
2 points
teamsolid
12 days ago
2 comments
336.
▲
Show HN: Paper Lantern – improving Autoresearch with research knowledge
(paperlantern.ai)
2 points
paperlantern
2 months ago
2 comments
337.
▲
Show HN: CVD Tool – Image Compression Algorithm (13MB to 10KB)"
(github.com/mohamedtrigui5-lab)
2 points
mohamedtrigui5
2 months ago
2 comments
338.
▲
C2PM(Color to Pixel Map)
2 points
Yukesh_J
6 months ago
2 comments
339.
▲
I built an open-weights memory system that reaches 80.1% on the LoCoMo benchmark
2 points
ViktorKuz
6 months ago
2 comments
340.
▲
Show HN: OS Yamato – A Wabi-Sabi OS Just Got an Upgrade
(github.com/osyamato)
2 points
tsuyoshi_k
10 months ago
2 comments
341.
▲
Ask HN: How LLMs Learn to Be "Generative"?
2 points
metalwhale
2 years ago
2 comments
342.
▲
Show HN: Mixlab, an ML arch lab in Go. JSON config, Metal and CUDA, 1.6s builds
(github.com/mrothroc)
2 points
mrothroc
a month ago
1 comment
343.
▲
Show HN: Lore – A reasoning engine that stores the "why" behind code changes
2 points
almonerthis
5 months ago
1 comment
344.
▲
Show HN: Loft CLI – Fine-tune and run LLMs (1–3B) on 8 GB MacBook Air, no GPUs
2 points
dips2umar
a year ago
1 comment
345.
▲
Show HN: MutAnt: Decentralized public/private mutable key-value storage
(github.com/Champii)
2 points
champii
a year ago
1 comment
346.
▲
Show HN: LLM-Rosetta - Translate LLM API Calls Across OpenAI, Anthropic, Gemini
(github.com/Oaklight)
2 points
Oaklight
2 months ago
discuss
347.
▲
Show HN: MaximusLLM – Train 262k-vocab LLMs on a single 16GB GPU
(github.com/yousef-rafat)
2 points
yousef_g
3 months ago
discuss
348.
▲
Show HN: Dspx – Native C++ DSP Library for Node.js Built for AWS Lambda (1.3MB)
2 points
a-kgeorge
3 months ago
discuss
349.
▲
Show HN: Local memory layer for AI agents, survives restarts, no embeddings
(screenapp.io)
2 points
JosephjackJR
3 months ago
discuss
350.
▲
Show HN: Ket – quantum circuit simulator, TypeScript, 3 back ends, 14 formats
(github.com/dmvjs)
2 points
dmvjs
3 months ago
discuss
351.
▲
Show HN: Msplat – 3D Gaussian Splatting training in ~90s on M4 Max, native Metal
(github.com/rayanht)
2 points
rayanht
3 months ago
discuss
352.
▲
Show HN: Sleeping LLM – A language model that remembers by sleeping
(github.com/vbario)
2 points
vbaranov87
3 months ago
discuss
353.
▲
Show HN: HS5 – Open Source fast single-node S3 compatible object storage
(hs5.eu)
2 points
uroni
4 months ago
discuss
354.
▲
Show HN: Spheni – A Vector Search Engine in C++ built from scratch, for Python
(github.com/datavorous)
2 points
datavorous_
4 months ago
discuss
355.
▲
Show HN: BPU – Reliable ESP32 Serial Streaming with Cobs and CRC
(github.com/choihimchan)
2 points
octablock
4 months ago
discuss
356.
▲
Show HN: LayerClaw – Observability tool for PyTorch training
2 points
prabhavsanga
4 months ago
discuss
357.
▲
Show HN: AgentHub – A unified SDK for LLM APIs with faithful validation
(github.com/Prism-Shadow)
2 points
PrismShadow
4 months ago
discuss
358.
▲
Show HN: Tiny Diffusion – Minimal diffusion LM in 364 lines
(github.com/nathan-barry)
2 points
nathan-barry
5 months ago
discuss
359.
▲
Show HN: A web-based lighting controller built because my old became a brick
(github.com/Arian-Ott)
2 points
arianott
5 months ago
discuss
360.
▲
Show HN: brig – a devcontainer CLI in Go
(github.com/nlsantos)
2 points
nsantos
6 months ago
discuss
More