The entire deep learning paradigm, including backpropagation, can be viewed as a form of in-context learning. This reframes the pre-training phase not as a separate process, but as the model forming a long-term associative memory, unifying it with inference-time adaptation.

AI agents need a multi-faceted memory architecture inspired by human cognition. This includes episodic (time-stamped events), semantic (world knowledge), procedural (workflows and skills), and working memory (immediate context window).

The "Attention is All You Need" paper's key breakthrough was an architecture designed for massive scalability across GPUs. This focus on efficiency, anticipating the industry's shift to larger models, was more crucial to its dominance than the attention mechanism itself.

A common misconception is that Transformers are sequential models like RNNs. Fundamentally, they are permutation-equivariant and operate on sets of tokens. Sequence information is artificially injected via positional embeddings, making the architecture inherently flexible for non-linear data like 3D scenes or graphs.

The core transformer architecture is permutation-equivariant and operates on sets of tokens, not ordered sequences. Sequentiality is an add-on via positional embeddings, making transformers naturally suited for non-linear data structures like 3D worlds, a concept many practitioners overlook.

The 'attention' mechanism in AI has roots in 1990s robotics. Dr. Wallace built a robotic eye with high resolution at its center and lower resolution in the periphery. The system detected 'interesting' data (e.g., movement) in the periphery and rapidly shifted its high-resolution gaze—its 'attention'—to that point, a physical analog to how LLMs weigh words.

The "memory" feature in today's LLMs is a convenience that saves users from re-pasting context. It is far from human memory, which abstracts concepts and builds pattern recognition. The true unlock will be when AI develops intuitive judgment from past "experiences" and data, a much longer-term challenge.

The key to continual learning is not just a longer context window, but a new architecture with a spectrum of memory types. "Nested learning" proposes a model with different layers that update at different frequencies—from transient working memory to persistent core knowledge—mimicking how humans learn without catastrophic forgetting.

Contrary to common perception shaped by their use in language, Transformers are not inherently sequential. Their core architecture operates on sets of tokens, with sequence information only injected via positional embeddings. This makes them powerful for non-sequential data like 3D objects or other unordered collections.