Mercor acquires Deeptune to build AI training environments
mercor.com · 642 words · saved by 1 readers
Mercor's five million experts plus Deeptune's platform make it possible to build realistic training environments across more industries and roles.
Today's frontier AI models can pass nearly any exam you give them, but put an agent inside a real workflow and it stalls on the first task an entry-level employee could handle. This is because the model lacks experience. Experience comes from doing real work: navigating messy documents, legacy enterprise software, and sprawling company context while making hundreds of small decisions along the way. It means knowing what to do when something breaks or when the next step isn't obvious. A model learns to perform well only by practicing repeatedly in the environment where the work takes place.…
saved by
related reading
- Expert Data for Frontier AI - AfterQueryafterquery.com
- Sweatshop data is overmechanize.work
- RL Environments and RL for Science: Data Foundries and Multi-Agent Architecturesnewsletter.semianalysis.com
- EdgeBench | Scaling Laws of Environment Learningedge-bench.org
- The Era of Experience Paper.pdfstorage.googleapis.com
- A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
- Sporks of AGIsergeylevine.substack.com
- A World of Verifiable Domainsseancai.com
- Low Latency and Model Training at Modalrhea24.github.io
- Mechanize, Inc.mechanize.work