Environments as a bottleneck in AGI development

📖 Description

Given a training environment or dataset, a training algorithm, an optimiser, and a model class capable of implementing an AGI (with the right parameters), there are two interesting questions we might ask about how conducive that environment is for training an AGI. The first is: how much do AGIs from that model class outperform non-AGIs? The second is: how straightforward is the path to reaching an AGI? We can visualise these questions in terms of the loss landscape of those models when evaluated on the training environment. The first asks how low the set of AGIs is, compared with the rest of the landscape. The second asks how favourable the paths through that loss landscape to get to AGIs are - that is, do the local gradients usually point in the right direction, and how deep are the local minima?

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/vqpEC3MPioHX7bv4t/environments-as-a-bottleneck-in-agi-development