ChatGPT runs its own search index family, Labrador, and is A/B testing it against scraped results
VeryWellVersed · x · 2026-09-06
Peec AI's analysis upends the SEO assumption that ChatGPT only retrieves via Bing and Google: OpenAI has spent years building its own retrieval stack, internally called Labrador — not one index but a family of vertical indexes covering web, PDF, YouTube, news, arXiv, Wikipedia, local, finance, legal, medical, shopping, and images. Between May 21 and July 21, 2026, a resultsource field in ChatGPT server-side events showed only four values: Labrador, Bright, Oxylabs, and SERP, the latter three being external scraping providers. Google antitrust testimony and job postings confirm a deliberate years-long build; ChatGPT is now A/B testing its own index against scraped results, most visibly in shopping. It also caches pages instead of fetching live, and pulls from at least eight other providers including Yelp, TripAdvisor, and Microsoft's Web IQ. Key takeaway: a ChatGPT strategy stopping at Bing misses most of the system.
More from Companies & People
- Yang Zhilin left a US career to build Moonshot AI, now shaking global markets — pstAsiatech · 2026-09-06
- Ex-Employee: Problems at Musk's Other Companies Made My Job Feel Easy — yunta_tsai · 2026-09-06
- OpenAI ambassadors run community hackathon in Singapore teaching students, seniors and lawyers — gabrielchua · 2026-09-06
- Founder calls Meta 'a case study of what not to do', citing layoffs and AI missteps — bindureddy · 2026-09-06
- Ashoka-backed CRASHLabAI hiring Clinical Research Lead for Indian medical LLM benchmarks — DrDatta_AIIMS · 2026-09-06
- Moderna Soars 176% as Personalized mRNA Cancer Vaccine Hits Positive Phase 3 in Melanoma — 快鲤鱼 · 2026-09-06