Search: github.com/training | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

811.

Show HN: Trained a 12M transformer on an ML framework we built from scratch

github.com/mni-ml

2 months ago

2 points

812.

Show HN: The Slow AI Commons – here's why it might fail

github.com/aNobodyfrom76

8 months ago

2 points

813.

Ask HN: How LLMs Learn to Be "Generative"?

2 years ago

2 points

814.

The Science of Accelerated Playback

3 years ago

2 points

815.

Ask HN: What are the best tools for extracting tax data from a W2 form?

5 years ago

2 points

816.

Bug Fixes for Larkos

16 days ago

2 points

817.

The Key Lime Pie Benchmark

2 months ago

2 points

818.

Show HN: I built a <400ms latency voice agent that runs on a 4gb vram GTX 1650"

github.com/pheonix-delta

5 months ago

2 points

819.

Show HN: An Implementation of DataRater: Meta-Learned Dataset Curation

github.com/rishabhranawat

9 months ago

2 points

820.

InfoSeek: The First Open-Source Framework for Deep Research Data Synthesis

9 months ago

2 points

821.

Show HN: Loft CLI – Fine-tune and run LLMs (1–3B) on 8 GB MacBook Air, no GPUs

a year ago

2 points

822.

Show HN: Automated Kafka client and broker optimization

github.com/DattellConsulting

a year ago

2 points

823.

Show HN: Interactive first-principles climate physics simulation with explainer

earth.crackalamoo.com

a month ago

2 points

824.

Show HN: Toposonico, a music recommender you can navigate

2 months ago

2 points

825.

Prism License Framework (a modular license generator)

2 months ago

2 points

826.

Show HN: MoodSense AI – mood detection and recommendations from text

2 months ago

2 points

827.

Show HN: 3 out of 4 devs failed to catch dangerous AI-suggested commands

agentsaegis.com

3 months ago

2 points

828.

Show HN: Experiments Mapping the "Primitive Layer" in Language Models

github.com/dchisholm125

3 months ago

2 points

829.

Sumi – Open-source voice-to-text with local AI polishing

4 months ago

2 points

830.

Show HN: DocMCP – Index any docs site locally, search it from Claude via MCP

4 months ago

2 points

831.

Low-entropy tokens tolerate substitution with and 0.1 PPL cost across models

4 months ago

2 points

832.

Show HN: Neural Siege – A Multi-Agent RL Combat Simulation

github.com/ayushdnb

4 months ago

2 points

833.

Show HN: AndroJack – A grounding gate for Android AI assistants

github.com/VIKAS9793

4 months ago

2 points

834.

Show HN: A production-style recommender using vector retrieval and re-ranking

4 months ago

2 points

835.

Show HN: Sleeping LLM – A language model that remembers by sleeping

github.com/vbario

4 months ago

2 points

836.

Show HN: Echos – Self-hosted AI knowledge base for things you forget

github.com/albinotonnina

4 months ago

2 points

837.

Show HN: I solo-validated Fed learning at 10M nodes with 50% Byzantine tolerance

github.com/rwilliamspbg-ops

4 months ago

rwilliamspbgops

2 points

838.

Show HN: Open-source MCP servers making every country's law searchable by AI

4 months ago

2 points

839.

Ask HN: Why does single-node DDP sometimes get slower with more GPUs?

4 months ago

2 points

840.

Show HN: PlanOpticon – Extract structured knowledge from video recordings

github.com/ConflictHQ

4 months ago

2 points