Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
601.
Show HN: Forget bash, write your shell scripts in plain English (github.com/statico)
2 points
statico
a year ago
3 comments
602.
Show HN: LLMEasyTools – Tools for LLM agents (Python lib) (github.com/zby)
2 points
zby
2 years ago
3 comments
603.
LLM quantization severely damages model quality and perplexity (github.com/ggerganov)
2 points
behnamoh
3 years ago
3 comments
604.
Llama.cpp with CUDA Support on Original Jetson Nano (4GB) (github.com/kreier)
2 points
Abishek_Muthian
2 months ago
2 comments
605.
A tool to tell you what LLMs can run on your machine (github.com/AlexsJones)
2 points
thinkingaboutit
3 months ago
2 comments
606.
Show HN: LLMuxer – Find the cheapest LLM that keeps your accuracy (github.com/mihirahuja1)
2 points
mihir_ahuja
10 months ago
2 comments
607.
Can LLMs accurately evaluate their own confidence? (github.com/anerli)
2 points
anerli
a year ago
2 comments
608.
LLaVA-Mini: Efficient Image and Video Large Multimodal Models (github.com/ictnlp)
2 points
Vily
a year ago
2 comments
609.
LLM Catcher – Automated Python Debugging Using LLMs (github.com/d4v3y0rk)
2 points
d4v3y0rk
a year ago
2 comments
610.
GPT-4o's Memory Breakthrough (github.com/llmonpy)
2 points
sftombu
2 years ago
2 comments
611.
LLaMA Terminal Completion, a local virtual assistant for the terminal (github.com/adammpkins)
2 points
adammpkins
3 years ago
2 comments
612.
Web benchmark: Dlang (601.74 req/sec) vs. Node.js (300.80 req/sec) (github.com/llaine)
2 points
darksioul
10 years ago
2 comments
613.
Run your own local LLM with rate limits via API-keys (github.com/skorotkiewicz)
2 points
modinfo
10 days ago
1 comment
614.
Show HN: A seed prompt that bootstraps a custom knowledge-base system (github.com/dah)
2 points
dnh44
22 days ago
1 comment
615.
Show HN: LLM-context-base – Git template for LLM-powered personal wikis (github.com/asakin)
2 points
asakin
2 months ago
1 comment
616.
Run and manage open-source LLMs from your terminal (github.com/ThomasRochefortB)
2 points
clanking7150
2 months ago
1 comment
617.
Show HN: Liteparse, an OSS universal fast document parser by LlamaParse team (github.com/run-llama)
2 points
pierre
3 months ago
1 comment
618.
Generate and play music playlists on Apple music (github.com/GNtousakis)
2 points
todsacerdoti
6 months ago
1 comment
619.
LLM Council – Your Local Multi-Model AI Advisory Board (github.com/karpathy)
2 points
the-mitr
6 months ago
1 comment
620.
Lolcode Linter – End-to-End Pipeline (Lexer → Parser → Analyzer) in Rust (github.com/jerankda)
2 points
jerankda
6 months ago
1 comment
621.
LLM Security Guide – 100 tools and real-world attacks from 370 experts (github.com/requie)
2 points
tarique192
7 months ago
1 comment
622.
Llmswap: Avoid LLM vendor lock-in – 10 providers with top LMArena models (github.com/sreenathmmenon)
2 points
sreenathmenon
8 months ago
1 comment
623.
Llmnop, a tiny Rust rewrite of LLMPerf (github.com/jpreagan)
2 points
jpreagan
a year ago
1 comment
624.
Kimi-cc: Use Kimi latest model(kimi-k2-0711-preview) to drive your Claude Code (github.com/LLM-Red-Team)
2 points
simonpure
a year ago
1 comment
625.
Tencent launches a new generation of fast thinking model Hunyuan Turbo S (github.com/Tencent)
2 points
Terretta
a year ago
1 comment
626.
Hello World – Enterprise Edition (2015) (gist.github.com)
2 points
petee
a year ago
1 comment
627.
The Fil-C Manifesto: Garbage In, Memory Safety Out (github.com/pizlonator)
2 points
pabs3
2 years ago
1 comment
628.
Rate limiter for LLMs outperforms exponential backoff (github.com/llmonpy)
2 points
sftombu
2 years ago
1 comment
629.
LLvee – LLVM AI (github.com/githubbin765)
2 points
zaqwedccdertgb
2 years ago
1 comment
630.
A lightweight and extensible ls alternative [Tools] (github.com/triyanox)
2 points
triyanox
2 years ago
1 comment
More