FundamentalsRotary Embeddings (RoPE) Explained With Clock Hands
RoPE encodes position by rotating vectors rather than adding to them. Why that gives relative distance for free, and how it made 1M context possible.
ReadNotes on models, agents, and what inference costs
Practical writing for developers building with large language models — how they work, how to pick one, and how to keep the bill predictable.
Fundamentals
ModelsRunning Frontier Models on Rented GPUs: What It Really Takes
Renting GPUs to serve open weights sounds like a shortcut past API pricing. The memory maths, the utilisation problem, and when it actually pays off.
Read
FundamentalsScaling Laws Explained: What Predicts a Model Getting Better
Scaling laws describe how loss falls as compute, data and parameters grow. What they actually claim, where they stopped applying, and why it matters to you.
Read
AI AgentsScratchpad Patterns: Giving an Agent Somewhere to Think
A durable scratchpad survives compaction, crashes and handoffs. What belongs on it, what does not, and how to stop it becoming a second transcript.
Read
ModelsSecurity Review for Open-Weight Models Before You Deploy
Downloading weights means running someone else's artefact inside your network. What to check on provenance, licence, serving stack and data flow.
Read
FundamentalsSelf-Consistency Decoding: Ask Five Times, Take the Majority
Sampling several answers and voting beats a single answer on some tasks and is pure waste on others. The mechanism, the cost, and when to reach for it.
ReadAI AgentsShared Memory Between Agents: Designs That Actually Hold
Agents that share a scratchpad drift, overwrite and confuse each other. Here are four shared-memory designs, what each one breaks, and how to pick.
Read
Cost & PricingShowback Reporting for AI Spend Teams Will Actually Read
How to report LLM spend back to engineering teams without billing them: what a useful report contains, what cadence works, and which unit metrics survive scrutiny.
Read
FundamentalsSparse vs Dense Activation: What Runs on Every Token
Sparse activation means most of a model sits idle for any given token. That single fact explains model pricing, memory bills and misleading spec sheets.
Read
AI AgentsSpeculative Agent Execution: Running Ahead of the Decision
Agents spend most of their wall-clock time waiting. Speculative execution starts likely next steps early and discards the wrong guesses. Here is when it pays.
ReadFundamentalsSpeculative Decoding in Practice: When It Pays Off
Speculative decoding is standard in serving stacks now, but the speedup is workload-dependent. What decides whether it helps you, and how to tell.
Read
FundamentalsStop Sequences Explained: Ending Generation on Purpose
How stop sequences work, why they interact badly with tokenisation and streaming, and the finish_reason check most integrations forget to make.
ReadShowing 229–240 of 404 articles