# Stanley argues open-endedness is essential to AGI but hard to benchmark

> Original title: ARC Prize Research Summit - @kenneth0stanley

- Source: ARC Prize
- Published: 2026-11-06T17:33:05.000Z
- Bad Influence: https://badinfluence.news/items/me4jnw0hc09k8jl9hdphtyvgq
- Original: https://x.com/arcprize/status/2118758583836049421

## Summary

Kenneth Stanley, speaking at the ARC Prize Research Summit, argues that open-endedness, invention, and discovery are essential to AGI. He says designing a benchmark for these capabilities creates difficult problems.

## Post

ARC Prize Research Summit - @kenneth0stanley

On why open-endedness, invention, discovery are essential to AGI, but designing a benchmark for them creates difficult problems.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2118484345459810304%2Fimg%2F3lt7gISzrlcAYxWg.jpg&mode=thumb&exp=1794182400&sig=5c718023b7bed631)