lumimax tested: page-level citations, catches contradicting RAG papers
dr_cintas · x · 2026-11-20
KOL drcintas tested lumimax, a Chinese knowledge-base product claiming top scores on all eight public benchmarks, feeding it GraphRAG, LightRAG, HippoRAG 1/2 papers plus Karpathy's LLM Wiki gist. It answered with page-level citations, caught the papers contradicting each other on LightRAG's ranking, and admitted when sources didn't cover a question. Via MCP, Claude Code queried the same knowledge base and wrote a memo separating document evidence from web results. Humans still decide which paper's numbers to trust.
More from coding & agent
- Running ComfyUI fully via Claude in a container — no manual UI anymore — xWranglerWranglerx · 2026-11-20
- AI writes all code to make a real robotic arm play chess, open-sourced — FinanceYF5 · 2026-11-20
- trace2rules audits AGENTS.md against real sessions: 66 rules, only 9 measurable, cargo fmt ignored 100% — rkkautsar · 2026-11-20
- Amazon's CompoundingKernel Hits #1 on SOL-ExecBench with Self-Improving GPU Kernel Agents — AmazonScience · 2026-11-20
- Indie dev builds a personal bot with Fable 5.2 + T3 Code, linking X and Meta data via a shared knowledge base — yihui_indie · 2026-11-20
- Clairvoyance 0.91 ships Agentic Web browser for Claude and Codex — draginol · 2026-11-20