The journal

Notes from the context layer.

Engineering deep-dives, benchmarks and customer stories on persistent code context, knowledge graphs, and the AI coding tools we work with daily.

All 109 Customers 20 Engineering 89

51–60 of 109 · page 6 of 11

Mar 31, 2026 AI coding tool comparisonClaude Code vs Cursor vs CopilotAI coding agent problems

Every AI Coding Tool Has the Same Problem. None of Them Will Tell You.

Claude Code, Cursor, Copilot, Codex — they all share the same fundamental flaw: no persistent memory, brute-force file reading, and context that fills up and gets thrown away. Here's what none of them admit.

Mar 31, 2026 Flash AttentionGPU optimizationSRAM

Flash Attention: How One Paper Made Long Context Possible

Flash Attention never materializes the full n×n attention matrix. Instead, it computes in tiles using fast GPU SRAM. Here's how it works and why it's 2-4× faster.

Mar 31, 2026 future of AIstate space modelsMamba

The Future: Will Context Windows Grow Forever? (Ring Attention, SSMs, Retrieval-Augmented Everything)

Three competing paradigms: grow context via hardware, replace attention with O(n) alternatives like Mamba, or build external memory systems. Which will win?

Mar 31, 2026 GPU memorymemory wallVRAM requirements

The Quadratic Memory Wall: A Precise Analysis of GPU Memory Requirements per Context Length

Total GPU memory = model weights + KV cache + activations + workspace. Here's the exact formula to compute maximum context length for any GPU configuration.

Mar 31, 2026 Infini-Attentioncompressive memoryinfinite context

Infini-Attention and Compressive Memory: Unbounded Context with Bounded Memory

Google's Infini-Attention combines standard attention with a compressive memory that persists across segments — enabling theoretically infinite context at O(1) memory.

Mar 31, 2026 information theoryShannonchannel capacity

The Information-Theoretic Limits of Context Windows

There are fundamental limits on how much information a fixed-width attention mechanism can extract from n tokens. Here's the math from Shannon's channel capacity to attention bounds.

Mar 31, 2026 KV cache GPU memoryVRAM

The KV Cache: Why Your AI Needs So Much GPU Memory

During inference, the model stores Key and Value vectors for every token. This KV cache is often the biggest memory consumer. Here's the math behind it.

Mar 31, 2026 KV cacheVRAM calculationGPU memory

KV Cache Memory Math: Calculating Exactly How Much VRAM You Need

The exact formula for KV cache memory and worked examples for every major model architecture. Calculate your GPU requirements precisely.

Mar 31, 2026 lost in the middleattention distributionprompt engineering

The 'Lost in the Middle' Problem: Why Your AI Ignores Information in the Center of Long Prompts

Research proved that LLMs attend strongly to the beginning and end of context but poorly to the middle. This is a mathematical property, not a bug.

Mar 31, 2026 MQAGQAmulti-query attention

Multi-Query Attention and Grouped-Query Attention: Reducing KV Cache by 8× at the Architecture Level

Standard multi-head attention uses separate K and V for each head. MQA and GQA share them — reducing KV cache dramatically with minimal quality loss.