Corbenic
Re:The GPU never reads the same text twice
on Monday October 19, 2026 @05:31AM (#50150267)
https://github.com/corbenicai/galahad - free tot test and we love to get feedback . so thank you to post
Show HN: Long term Memory and 50M token window for LLM
Long-Term Memory for AI:50M-Token Window,Is Faster,Cheaper Than Recompute
Re:Startup Corbenic AI launches Galahad to secure AI memory and cut en...
on Friday October 02, 2026 @08:44AM (#49932880)
https://arxiv.org/abs/2609.39358 this is the paper
Show HN: KV-Cache Grafting – Boosting frozen 12B LLMs to 93.3% AIME accuracy
Re:Show HN: Taliesin – bit-exact KV-cache restore, 21x faster, cross-G...
on Friday June 05, 2026 @07:53AM (#48411173)
Thank you , and thanks for the support , But we fear people of ycombinator did not see our apliation or did not see our progress. But thank you all kind works help us grow
Re:Show HN: Taliesin – bit-exact KV-cache restore, 21x faster, cross-G...
on Thursday June 04, 2026 @04:26PM (#48404147)
Thanks , We hope some pepople of yc also see this.
Re:Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
on Wednesday May 13, 2026 @11:22AM (#48123148)
Great work Henry!