Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
1.
Show HN: A React grid component (github.com/ggordan)
2 points
ggordan
11 years ago
discuss
2.
Star Wars Arrays (github.com/giordano)
2 points
us-merul
3 years ago
discuss
3.
Show HN: Notte – Full-stack web-agent framework (open-source) (github.com/nottelabs)
3 points
giordanol
a year ago
discuss
4.
Show HN: Web Components SSR and hydration in 1KB– just a decorator, no framework (github.com/alexandregiordanelli)
2 points
agiordanelli
10 months ago
discuss
5.
Show HN: I made web agents reliable with smaller LLMs via natural language (github.com/nottelabs)
2 points
giordanol
a year ago
discuss
6.
Show HN: An Interactive Debugger MCP Server (github.com/BloopAI)
7 points
ggordonhall
a year ago
discuss
7.
Show HN: Port of OpenAI's Whisper model in C/C++ (github.com/ggerganov)
399 points
ggerganov
3 years ago
87 comments
8.
Show HN: WasmGPT – “ChatGPT” in the browser, no WebGPU and no server needed (lxe.co)
185 points
lxe
3 years ago
50 comments
9.
Show HN: Project S.A.T.U.R.D.A.Y. – open-source, self hosted, J.A.R.V.I.S. (github.com/GRVYDEV)
121 points
GRVYDEV
3 years ago
30 comments
10.
Show HN: Windows port of OpenAI's Whisper automatic speech recognition model (github.com/Const-me)
43 points
Const-me
3 years ago
20 comments
11.
Show HN: TurboPilot: Copilot clone runs code completion LLM on your CPU (github.com/ravenscroftj)
37 points
DrRavenstein
3 years ago
4 comments
12.
Show HN: Grammar Generator App for Llama.cpp (grammar.intrinsiclabs.ai)
19 points
aduffy
3 years ago
6 comments
13.
Show HN: Penrose Pipes (penrosepipes.vercel.app)
17 points
fourthark
3 years ago
12 comments
14.
Ask HN: Are you training and running custom LLMs and how are you doing it?
15 points
kordlessagain
3 years ago
2 comments
15.
Show HN: Port42 – AI companions that build and act on your Mac (v0.5.0) (port42.ai)
5 points
gordonmattey
3 months ago
discuss
16.
Show HN: OpenTheo – Transcribed and searchable Bible teaching with Whisper.cpp (opentheo.com)
5 points
dinoleif
3 years ago
discuss
17.
Show HN: I built BakLLaVA and llama.cpp demo and it went viral on X
4 points
Obertr
3 years ago
1 comment
18.
Show HN: Cerebras-GPT-2.7B finetuned on Stanford Alpaca dataset (github.com/lxe)
4 points
lxe
3 years ago
1 comment
19.
Apple predicted the rise of local LLMs, hence the M2 Ultra
2 points
behnamoh
3 years ago
3 comments
20.
Show HN: Libgd-GIS – Render maps and GIS data directly in Ruby (GeoJSON → Image) (ggerman.github.io)
2 points
ggerman2025
4 months ago
discuss
21.
Show HN: Galene-stt: automatic captioning for the Galene videconferencing system (github.com/jech)
2 points
jech
2 years ago
discuss
22.
Show HN: bigWav.app – web based transcription powered by Whipser and WASM (bigwav.app)
2 points
emadda
3 years ago
discuss
23.
Need help breaking my programming language
1 point
joelg236
13 years ago
1 comment
24.
Llama.cpp 30B runs with only 6GB of RAM now (github.com/ggerganov)
1311 points
msoad
3 years ago
414 comments
25.
Llama.cpp: Port of Facebook's LLaMA model in C/C++, with Apple Silicon support (github.com/ggerganov)
989 points
mrtksn
3 years ago
284 comments
26.
Llama.cpp: Full CUDA GPU Acceleration (github.com/ggerganov)
728 points
gzer0
3 years ago
310 comments
27.
Talk-Llama (github.com/ggerganov)
474 points
plurby
3 years ago
140 comments
28.
Llama: Add grammar-based sampling (github.com/ggerganov)
417 points
davepeck
3 years ago
105 comments
29.
New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy (github.com/ggerganov)
382 points
weinzierl
2 years ago
72 comments
30.
Serverless, peer-to-peer, local file sharing through sound (github.com/ggerganov)
337 points
_fx6v
6 years ago
93 comments
More