_peregrine_
- Karma
- 174
- Created
- 4 years ago
About
technical writer + editor. I generally share stuff written by my peers. Currently @ turbopufferRecent Submissions
- 1. ▲ Training a Specialist Code Search Agent with Turbopuffer (appliedcompute.com)
- 2. ▲ The Shape and Feel of the Post-AI Data Stack (iandmacomber.com)
- 3. ▲ A graph-theoretic approach to building reliable LLM judges for retrieval (georgianailab.substack.com)
- 4. ▲ Mixing numeric attributes into text search for better first-stage relevance (turbopuffer.com)
- 5. ▲ How to build a distributed queue in a single JSON file on object storage (turbopuffer.com)
- 6. ▲ ANN v3: 200ms p99 query latency over 100B vectors (turbopuffer.com)
- 7. ▲ Designing inverted indexes in a KV-store on object storage (turbopuffer.com)
- 8. ▲ Why BM25 queries with more terms can be faster (and other scaling surprises) (turbopuffer.com)
- 9. ▲ Vectorized MAXSCORE over WAND, especially for long LLM-generated queries (turbopuffer.com)
- 10. ▲ Flink's 95% Problem (tinybird.co)