HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Ask HN: Open-source ChatGPT alternatives?
58 comments
3 years ago
baobabKoodaa
86 points
2.
▲
Show HN: My AI agents bully each other to prevent context drift
wuphf.team
discuss
a month ago
najmuzzaman
9 points
3.
▲
Show HN: UNet diffusion model in pure CUDA
github.com/clu0
discuss
2 years ago
clu0
8 points
4.
▲
Ask HN: What happened with Eureka Labs, Karpathy's startup?
discuss
24 days ago
alexmolas
6 points
5.
▲
Show HN: Revibing nanochat's inference model in C++ with ggml
github.com/k-ye
discuss
5 months ago
makechan
5 points
6.
▲
Ask HN: Open-source projects around LLM (APIs) and GPT?
1 comment
3 years ago
krishadi
3 points
7.
▲
Ask HN: How LLMs Learn to Be "Generative"?
2 comments
2 years ago
metalwhale
2 points
8.
▲
Show HN: PicoGPT v2 – GPT in <40 lines of vanilla JS running from a QR code
github.com/Kuberwastaken
1 comment
4 months ago
kuberwastaken
2 points
9.
▲
Show HN: Evo – parallel autoresearch experiments for Claude Code and Codex
github.com/evo-hq
discuss
2 months ago
abtom
2 points
10.
▲
Show HN: Shared team context for AI coding sessions with ambient intelligence
github.com/norrietaylor
discuss
2 months ago
torrienaylor
2 points
11.
▲
Show HN: AI agents who prevent context drift through gossip
wuphf.team
discuss
a month ago
najmuzzaman
1 points
12.
▲
Show HN: Karpathy's Autoresearch with Evolutionary Database
github.com/hgarud
discuss
3 months ago
hgarud
1 points
13.
▲
Show HN: MicroGPT-C – C99 GPT for Edge Training and Tiny Model Pipelines
github.com/enjector
discuss
4 months ago
Ajay__soni
1 points
14.
▲
Tell HN: Karpathy's MinGPT Works on Windows and AMD (Ryzen Max)
discuss
7 months ago
lostmsu
1 points
15.
▲
NanoGPT
github.com/karpathy
320 comments
3 years ago
trekhleb
1532 points
16.
▲
NanoChat – The best ChatGPT that $100 can buy
github.com/karpathy
308 comments
8 months ago
huseyinkeles
1523 points
17.
▲
Llm.c – LLM training in simple, pure C/CUDA
github.com/karpathy
168 comments
2 years ago
tosh
1050 points
18.
▲
Llama2.c: Inference llama 2 in one file of pure C
github.com/karpathy
165 comments
3 years ago
anjneymidha
707 points
19.
▲
Reproducing GPT-2 in llm.c
github.com/karpathy
117 comments
2 years ago
tosh
618 points
20.
▲
Karpathy's MinGPT
github.com/karpathy
102 comments
6 years ago
aliabd
374 points
21.
▲
LLM Wiki – example of an "idea file"
gist.github.com
95 comments
3 months ago
tamnd
296 points
22.
▲
MinGPT: Minimal PyTorch re-implementation of GPT
github.com/karpathy
24 comments
4 years ago
memorable
223 points
23.
▲
Autoresearch: Agents researching on single-GPU nanochat training automatically
github.com/karpathy
58 comments
4 months ago
simonpure
208 points
24.
▲
Karpathy: Let's reproduce GPT-2 (1.6B): one 8XH100 node 24h $672 in llm.c
github.com/karpathy
58 comments
2 years ago
alecco
182 points
25.
▲
NanoGPT: The simplest, fastest repository for training medium-sized GPTs
github.com/karpathy
21 comments
2 years ago
ulrischa
114 points
26.
▲
Convolutional Neural Networks in your browser
github.com/karpathy
8 comments
12 years ago
abhikandoi2000
91 points
27.
▲
Code for the Byte Pair Encoding algorithm, commonly used in LLM tokenization
github.com/karpathy
31 comments
2 years ago
magoghm
81 points
28.
▲
Karpathy/Nano-Llama31
github.com/karpathy
1 comment
2 years ago
tim_sw
74 points
29.
▲
NeuralTalk2: Efficient Image Captioning code in Torch, runs on GPU
github.com/karpathy
23 comments
11 years ago
rshaban
66 points
30.
▲
Full forward pass of GPT-2 in one file of pure CUDA
github.com/karpathy
4 comments
2 years ago
tosh
63 points
More