Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
31.
80.1 % on LoCoMo Long-Term Memory Benchmark with a pure open-source RAG pipeline
3 points
ViktorKuz
6 months ago
discuss
32.
Show HN: An open-source DAW plugin built on JUCE, React, and Lyria RealTime (github.com/magenta)
2 points
DesaiAshu
3 months ago
discuss
33.
Show HN: BreakMyAgent – Open-source red-teaming sandbox for LLM system prompts
2 points
breakmyagent
3 months ago
discuss
34.
Show HN: Solving ARC AGI 2 with interleaved thinking and stateful IPython REPL (github.com/gutfeeling)
2 points
steinsgate
4 months ago
discuss
35.
Show HN: My 16MB vibe-coded voice cloning app (github.com/blackboardsh)
2 points
yoav
4 months ago
discuss
36.
Show HN: Local Voice Assistant
2 points
armcat
4 months ago
discuss
37.
Show HN: We let GPT OSS 120B write and run Python and ARC AGI 2 jumped 4x (github.com/gutfeeling)
2 points
steinsgate
4 months ago
discuss
38.
Show HN: Tokiwi – An online tokenizer for any Hugging Face model (tokiwi.dev)
2 points
TweedBeetle
a year ago
discuss
39.
Show HN: MindMapp – Mind mapping app built by AI in 12 hours (mindm.app)
1 point
ChopSticksPlz
5 months ago
1 comment
40.
Show HN: Oo – compress output for coding agents (cargo test → "47 passed, 2.1s") (github.com/randomm)
1 point
jannniii
2 months ago
discuss
41.
Show HN: FretBench – I tested 14 LLMs on reading guitar tabs. Most failed (fretbench.tymo.ai)
1 point
jmcapra
3 months ago
discuss
42.
Show HN: Dwani.ai – AI for Indian Languages
1 point
gaganyatri
5 months ago
discuss
43.
80.1 % on LoCoMo Long-Term Memory Benchmark with a pure open-source RAG pipeline
1 point
ViktorKuz
5 months ago
discuss
44.
Show HN: Change the model. Same output. The pipeline decides. VAC Memory System
1 point
ViktorKuz
6 months ago
discuss
45.
Show HN: Metis Agent v0.6.1 – Run OpenAI's GPT OSS Locally with No API Keys (github.com/metisos)
1 point
cjohnsonpr
10 months ago
discuss