loaderchips
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Show HN: Motif Atlas – recurring patterns behind complex systems (nikitph.github.io)
- Show HN: Reward Is Not Reinforcement Until Admitted (github.com)
- Generative Intuition (nikitph.medium.com)
-
The fix for machine unlearning in vector databases turns out to be conceptually simple, but it requires changing the semantics of retrieval. Standard FAISS-style indices store vectors and compute: argmax ⟨q, vᵢ⟩ If you…
- Transformers Must Hallucinate (medium.com)
-
Hello HN community, Longtime lurker and really happy to be writing this post. I'm excited to share a proof of concept I've been working on for efficient vector database distribution called Ragged. In my paper and PoC, I…