Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
511.
▲
Show HN: LLM-as-a-Form
(github.com/claudeomusic)
3 points
claudeomusic
6 months ago
discuss
512.
▲
Show HN: LLM-models – a CLI tool to list available LLM models across providers
(github.com/ljbuturovic)
3 points
ljubomir
6 months ago
discuss
513.
▲
Explanation of Gated DeltaNet (Qwen3-Next and Kimi Linear)
(github.com/rasbt)
3 points
ModelForge
7 months ago
discuss
514.
▲
Show HN: Llumen – Lightweight LLM chat app that runs in <1s with OpenRouter
(github.com/pinkfuwa)
3 points
easonqq0000
8 months ago
discuss
515.
▲
Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20
(github.com/karpathy)
3 points
gmays
9 months ago
discuss
516.
▲
LLM-optimizer: Benchmark and optimize LLM inference across frameworks with ease
(github.com/bentoml)
3 points
djhu9
9 months ago
discuss
517.
▲
Disclaimer: I am not a webdev, this PR was vibe coded
(github.com/olegshulyakov)
3 points
WhereIsTheTruth
9 months ago
discuss
518.
▲
Qwen3 from Scratch
(github.com/rasbt)
3 points
tzury
10 months ago
discuss
519.
▲
LLM Bridge by Supermemory
(github.com/supermemoryai)
3 points
handfuloflight
a year ago
discuss
520.
▲
Show HN: Worflows.py, the best way to build agents
(github.com/run-llama)
3 points
pierre
a year ago
discuss
521.
▲
Qwen3 Implemented from Scratch
(github.com/rasbt)
3 points
sbbq
a year ago
discuss
522.
▲
Show HN: llm-tools-openapi and MCP: access to MCP server with this one trick
(github.com/Oliviergg)
3 points
oliviergg
a year ago
discuss
523.
▲
Show HN: A tagged template literal utility for clean LLM prompt generation
(github.com/davefowler)
3 points
thingsilearned
a year ago
discuss
524.
▲
Llmbasedos: Minimal Linux OS with a Model Context Protocol (MCP) Gateway
(github.com/iluxu)
3 points
tosh
a year ago
discuss
525.
▲
A tool for migrating and optimizing prompts from other LLMs to Llama
(github.com/meta-llama)
3 points
yawnxyz
a year ago
discuss
526.
▲
FilC: A memory-safe implementation of C and C++
(github.com/pizlonator)
3 points
kmavm
a year ago
discuss
527.
▲
Show HN: LLM-Mafia-Game: AI Models Competing in Mafia Matches
(github.com/guzus)
3 points
uncanny_guzus
a year ago
discuss
528.
▲
Show HN: LLMDog – Format your codebase for LLM interactions (JetBrains Plugin)
(github.com/doganarif)
3 points
arifliftos
a year ago
discuss
529.
▲
LLMRank – ranking LLMs using peer-based cross-evaluation and PageRank
(github.com/marquisdepolis)
3 points
larsiusprime
a year ago
discuss
530.
▲
LLMUnity: Create AI Characters in Unity with LLMs
(github.com/undreamai)
3 points
benuix
2 years ago
discuss
531.
▲
Show HN: Llmq – Pipe stuff in the shell to AI
(github.com/phildougherty)
3 points
phildougherty
2 years ago
discuss
532.
▲
Open source Claude Artifacts – built with Llama 3.1 405B
(github.com/Nutlope)
3 points
sabrina_ramonov
2 years ago
discuss
533.
▲
Show HN: Run Small Language Models (SLMs) Directly on the Browser with Llm.js
(github.com/rahuldshetty)
3 points
anonymousd3vil
2 years ago
discuss
534.
▲
Show HN: LLM-A* – Large Language Model Enhanced Incremental Heuristic Search
(github.com/SilinMeng0510)
3 points
cheeseisinsane
2 years ago
discuss
535.
▲
Show HN: LLM Hacking Database
(github.com/pdparchitect)
3 points
_pdp_
2 years ago
discuss
536.
▲
Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20
(github.com/karpathy)
3 points
georgehill
2 years ago
discuss
537.
▲
Distributed LLM Inference with Llama.cpp
(github.com/ggerganov)
3 points
tosh
2 years ago
discuss
538.
▲
Fewer if statements with Nothing instead of None
(github.com/llmonpy)
3 points
sftombu
2 years ago
discuss
539.
▲
Practical Llama 3 inference implemented in a single Java file
(github.com/mukel)
3 points
simonpure
2 years ago
discuss
540.
▲
Finetune a GPT Model for Spam Detection on Your Laptop in Just 5 Minutes
(github.com/rasbt)
3 points
rasbt
2 years ago
discuss
More