6 results
Titans introduces a neural memory module that updates itself via gradient descent at inference time, breaking the context-length ceiling of Transformers while staying near-linear in complexity.
CPU for complex control flow, GPU for large-scale parallel computation, TPU for matrix operations pushed to the extreme. For most engineers, the real decision is cloud inference on GPU vs CPU, and when a TPU rental is worth it.
KV Cache reduces autoregressive Transformer generation from O(n²) — recomputing the full sequence for every new token — to O(n) per step, which is the core reason modern LLM inference is fast enough to be usable.
Transformer self-attention is inherently orderless — positional encoding is the fix. From sinusoidal absolute encoding, to learnable absolute encoding, to relative positional encoding, to RoPE (Rotary Position Embedding): modern LLMs almost universally use RoPE because it requires no parameters, naturally encodes relative distances, and can be extended to longer sequences.
LLM output quality is determined at three distinct layers: token-level decoding strategy, task-level workflow design, and model-level reasoning capability. Knowing which layer your problem lives in is the fastest path to fixing it.
When an AI Agent performs poorly, it's not necessarily because the model is dumb. Starting from a small experiment where a Gemma 4 2B fixes a bug, this piece explains what a Harness is, how Harness Engineering differs from Prompt / Context Engineering, and how effective natural-language rules like agents.md really are.