HNHacker News
TopNewBestAskShowJobs

Corbenic

5 karma · joined May 3, 2026

Corbenic AI builds hyper-efficient infrastructure primitives that drastically reduce AI compute costs and data bloat in real-time.
submissionscomments

Show HN: Try Free Long-Term Memory for AI 50M-Token Window

github.com·4 pts·Corbenic·
1

Show HN: Long term Memory and 50M token window for LLM

huggingface.co·6 pts·Corbenic·
2

Long-Term Memory for AI:50M-Token Window,Is Faster,Cheaper Than Recompute

arxiv.org·4 pts·Corbenic·
0

Show HN: KV-Cache Grafting – Boosting frozen 12B LLMs to 93.3% AIME accuracy

arxiv.org·3 pts·Corbenic·
0

Open-source dedup tool that EOSE Labs uses for sovereign language fleet

pemos.ca·2 pts·Corbenic·
0

A 3.5 MB C++ engine for deterministic RAG deduplication hitting 30 GB/s

github.com·3 pts·Corbenic·
0