
| Agents working simultaneously in Navier-Stokes research | 10,000 (shown on screen) |
| Messages exchanged between agents | 2.7 million (shown on screen) |
| Output tokens generated during the research | 130 billion (shown on screen) |
| Open math problems solved by the internal model | Over 100 (author's claim) |
Who will this analysis save an hour?We’ll send the link with the “actually” takeaway — they won’t have to watch the whole video.
ИИ агенты (AI agents) are systems that combine reasoning with tool use to perform actions autonomously. Unlike simple chatbots, they can plan, execute tasks in a sandbox, observe results, and adjust their strategy until a goal is met.
OpenAI uses 'context compaction' via the Responses API. When an agent's context window is full, the system summarizes the history into a compact state while keeping the primary goal and key findings, allowing the agent to continue working indefinitely.
The video suggests several patterns: 'Manager' (one agent orchestrates sub-chats), 'Pair' (one producer, one reviewer), and 'Studio' (specialized agents owning specific domains like Art or Code). The key is to define clear boundaries and shared worklogs.
OpenAI achieved this by creating 'Agent Teams' that explore different hypotheses in parallel. These teams communicate across groups to share findings and avoid duplicating effort, all while following a unified 'Shared Worklog' to stay aligned on the final solution.