Mercor, the $10 Billion AI Training Data Startup, Confirms Major Breach From LiteLLM Supply-Chain Attack
Mercor — which provides training data to OpenAI, Anthropic, and Meta — confirmed it was compromised via the TeamPCP supply-chain attack on LiteLLM. Lapsus$ claims 4TB of stolen data including source code, Slack logs, and recordings of AI-contractor conversations. This is the first confirmed high-profile casualty of the attack we covered last week.