Total Articles: 3 from 3 sources
Airbnb Engineering
1. CASTLE: training natural language search before the first real query
Published: 2026-10-13 17:01
Summary:
Promptagator [2] improves query diversity using few-shot examples, but is still limited by the gap between its generation distribution and real user behavior.In this post, we describe Contrastive And Seed-guided Training for natural Language sEarch (CASTLE), our framework for jointly generating queries and producing relevance labels from Airbnb’s own de-identified booking data Crucially, what is “positive” and “negative” is determined by actual, previous user booking behavior, not by the LLM itself, so there is no circularity in the subsequent generation of relevance labels.CASTLE architecture overview — contrastive listing pairs feeding into seed-guided query generationQuery generation Contrastive listing pairs from booking sessions ground query generation in real platform behavior and provide relevance labels by construction, while LLM prompting provides the query diversity and linguistic variety that behavioral data alone cannot supply
Cloudflare Engineering
1. Inside Hyperdrive: How we solved a rare Hyperdrive MySQL caching bug
URL: https://blog.cloudflare.com/hyperdrive-mysql/
Published: 2026-10-14 13:00
Summary:
While adding MySQL support to Hyperdrive, we found a subtle protocol bug when caching query results Here is how we tracked down a 0.001% rate error and made Hyperdrive MySQL generally available.
GitHub Blog
1. GitHub’s model for secret detection: Finding more secrets with less noise
Published: 2026-10-13 17:56
Summary:
GitHub’s context-aware secret classifier improves detection quality, raises weighted acceptance by 11.5%, and reduces median scan execution time by 86% The post GitHub’s model for secret detection: Finding more secrets with less noise appeared first on The GitHub Blog.
Generated on 2026-10-14 14:18:46