Weaviate Podcast: UC Berkeley PhD on whether long-context LLMs kill or improve RAG
CShorten30 · x · 2026-10-01
A new Weaviate Podcast episode features Siddhart Gollapudi, a UC Berkeley PhD student, discussing long-context LLMs vs. search and his recent paper "Can Language Models…". Key threads: is RAG dead or here to stay; are long context and search competing or complementary; and how research on each can improve the other. Relevant for developers working on retrieval-augmented and long-document pipelines.
Related event: Long-Context LLMs vs. RAG: Rivals or Allies?(2 posts)→
More from coding & agent
- Giving an AI agent a full real work task: research, planning, execution, deliverables — HeyToha · 2026-10-01
- Hugging Face open-sources Tau, a readable terminal coding agent built to teach — mervenoyann · 2026-10-01
- exe.dev: stop stacking agents, use a fast model for human comms — davidcrawshaw · 2026-10-01
- Open-Source Coding Model IQuest-Q1 Hits Hugging Face, Works with Claude Code — ZabihullahAtal · 2026-10-01
- IQuest-Q1 turns a written brief into a working SaaS dashboard — ZabihullahAtal · 2026-10-01
- ParallelPilot paper: 63% higher throughput for parallel coding agents — erichorvitz · 2026-10-01