ARK AGI 3
One of the evaluation attempts built around the ARC benchmark, used to assess AGI-related capabilities. Its report drew attention for isolating harness variables.
Timeline (last 90 days)
In the ARK AGI 3 report, OpenAI enabled two harness settings (preserving the model's reasoning process across steps, and summarizing history rather than truncating it), allowing the model to take more actions and pass more levels under the same number of output tokens.
OpenAI's experiments in ARK AGI 3 show that under the same output token budget, using summarization rather than truncation lets the model complete more effective actions, indicating that context management strategy and model capability are multiplicative rather than additive.
All Facts (2)
In the ARK AGI 3 report, OpenAI enabled two harness settings (preserving the model's reasoning process across steps, and summarizing history rather than truncating it), allowing the model to take more actions and pass more levels under the same number of output tokens.
50%UnverifiedOpenAI's experiments in ARK AGI 3 show that under the same output token budget, using summarization rather than truncation lets the model complete more effective actions, indicating that context management strategy and model capability are multiplicative rather than additive.
50%