OpenAI productizes multi-agent with Dots; o1 co-founder says gains overstated
At DevDay 2026, OpenAI pushed multi-agent work into its product line, launching Dots agents that can work around the clock: a personal Dot can call Codex for coding tasks, users and their Dots collaborate inside a shared Space, enterprise Specialist Dots take on specific duties, and an Agents API exposes harnesses, multi-agent control and computer-use capabilities to developers. OpenAI researcher Noam Brown, an early architect of o1 and later reasoning models, told podcast host Dwarkesh Patel that a system of 10,000 agents solved a Millennium Prize problem in 88 hours using about 130 billion tokens, but he would not credit even 10% of that to multi-agent coordination, saying a very strong general model did the real work. He said tests so far show 4 agents roughly doubling speed at double the cost, 16 agents behaving similarly but slightly less efficiently, gains running somewhat below linear and depending heavily on the task, and coordination efficiency at the 10,000-agent scale not yet well measured.
As agent count becomes a product selling point, a caution from inside OpenAI that capability comes mostly from the base model rather than coordination scale can help teams set realistic expectations for multi-agent bets.