Search: github.com/HughG | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

241.

Fine-tune your own Llama 2 to replace GPT-3.5/4

955 points

3 years ago

242.

Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model (github.com/cactus-compute)

776 points

24 days ago

243.

Show HN: Tabby – A self-hosted GitHub Copilot (github.com/TabbyML)

627 points

3 years ago

244.

Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep (github.com/MinishLab)

445 points

19 days ago

245.

Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview (github.com/dirac-run)

393 points

a month ago

246.

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning (github.com/unslothai)

385 points

3 years ago

247.

Show HN: Natural-SQL-7B, a strong text-to-SQL model (github.com/cfahlgren1)

362 points

2 years ago

248.

Show HN: Cactus – Ollama for Smartphones (github.com/cactus-compute)

231 points

a year ago

249.

Show HN: PromptTools – open-source tools for evaluating LLMs and vector DBs (github.com/hegelai)

211 points

3 years ago

250.

Show HN: Lantern – a PostgreSQL vector database for building AI applications (docs.lantern.dev)

196 points

3 years ago

251.

Show HN: Tune LLaMa3.1 on Google Cloud TPUs (github.com/felafax)

189 points

2 years ago

252.

Launch HN: Flower (YC W23) – Train AI models on distributed or sensitive data

180 points

3 years ago

253.

Show HN: Llama2 Embeddings FastAPI Server (github.com/Dicklesworthstone)

178 points

3 years ago

254.

Omnilingual ASR: Advancing automatic speech recognition for 1600 languages (ai.meta.com)

162 points

7 months ago

255.

Show HN: Axilla – Open-source TypeScript framework for LLM apps (github.com/axilla-io)

161 points

3 years ago

256.

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

153 points

2 years ago

257.

Show HN: liteLLM Proxy Server: 50+ LLM Models, Error Handling, Caching (github.com/BerriAI)

140 points

3 years ago

258.

Show HN: Klarity – Open-source tool to analyze uncertainty/entropy in LLM output (github.com/klara-research)

132 points

a year ago

259.

Launch HN: Cactus (YC S25) – AI inference on smartphones (github.com/cactus-compute)

123 points

9 months ago

260.

Show HN: I built a tensor library from scratch in C++/CUDA (github.com/nirw4nna)

119 points

a year ago

261.

Show HN: ArchGW – An intelligent edge and service proxy for agents (github.com/katanemo)

118 points

honorable_coder

a year ago

262.

Show HN: ART – a new open-source RL framework for training agents (github.com/OpenPipe)

116 points

a year ago

263.

Show HN: Local Privacy Firewall-blocks PII and secrets before ChatGPT sees them (github.com/privacyshield-ai)

111 points

6 months ago

264.

Show HN: Hyperparam: OSS tools for exploring datasets locally in the browser (hyperparam.app)

77 points

a year ago

265.

A complete open-source solution for accelerating Stable Diffusion!

75 points

4 years ago

266.

Show HN: TabPFN-2.5 – SOTA foundation model for tabular data (priorlabs.ai)

73 points

7 months ago

267.

Show HN: Open-source model and scorecard for measuring hallucinations in LLMs (vectara.com)

65 points

3 years ago

268.

Show HN: Using LLMs and Embeddings to classify application errors (github.com/highlight)

65 points

3 years ago

269.

Show HN: Lance – image/video generation and understanding in one model (github.com/bytedance)

64 points

16 days ago

270.

Show HN: AgentKit – JavaScript Alternative to OpenAI Agents SDK with Native MCP (github.com/inngest)

64 points

a year ago