Foundation Lab

Infinite Context Architectures

Turns entire repos/books into "single prompt" territory

Concept 100 of 100EfficiencyPhase 13

#100InfCtxEfficiency

key equationM_{t+1} = \text{Update}(M_t, K_t, V_t)

Selected Foundation Object

Keep the equation fixed; move through the evidence.

Concept 100 of 100InfCtxEfficiency / Phase 13: Cutting-edge 2024-2025 research

Current question

Compressive: old context summarized into memory state

M_{t+1} = \text{Update}(M_t, K_t, V_t)

PredictionCommit before the demo.

Ask what should change when the equation is manipulated, then let the visualization test that expectation.

EvidenceCompare local witness and source.

Use the runnable panel, the key equation, and canonical papers as separate forms of evidence for the same object.

InvariantName what survives notation changes.

The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.

Next moveContinue through the atlas.

Use prerequisites, dependents, and semantic links to repair the next gap without leaving the object behind.

What is still poorly explained in textbooks and papers:

If you want intuition first, start with the key equation and the visualization. Come back here for the full walkthrough.

Key Equation

M_{t+1} = \text{Update}(M_t, K_t, V_t)

Compressive memory for bounded cost:

\mathrm{Attn}(Q,K,V) = \mathrm{softmax}\left(\frac{QK^\top}{\sqrt{d}}\right)V \quad O(n^2)

Infini-attention: Maintain memory $M$ updated online, cost bounded w.r.t. $n$ .

Ring Attention: Distribute long sequences across devices via blockwise ring communication.

Munkhdalai et al.2024Google

Choose the next question to carry this object forward.