News & guides
Does Streaming Cost More? What You Actually Pay For
Streaming changes when tokens arrive, not how many are billed. Where it does affect spend, and the abandonment case that genuinely wastes money.
· 8 min read
DPO vs RLHF: Two Routes From Preferences to Model Behaviour
Direct preference optimisation drops the reward model and the RL loop. What that simplification buys, what it costs, and why open-weight work leans on it.
· 9 min read
Emacs LLM Setup: A Model Endpoint Without the Mouse
Wire an OpenAI-compatible endpoint into Emacs — package choices, auth-source instead of hardcoded keys, buffer versus region workflows, streaming and keybindings.
· 9 min readEscalation Rate: The Metric That Decides Your Default Model
The share of tasks your cheap model cannot finish decides whether a two-tier setup saves money or quietly doubles it. How to measure and act on it.
· 9 min read
Evaluating Models on Your Own Codebase
Public benchmarks rank a sample that is not your repository. How to choose tasks, source ground truth and size a set that actually predicts your work.
· 9 min read
Evaluating Prompt Changes Without Fooling Yourself
You edited a prompt and the output looks better. Here is how to find out whether it actually is, with paired runs, enough samples and judges you can trust.
· 9 min read
Every 1M-Context Model Compared: Which Window Is Real
Five open-weight models now advertise 1M tokens. Advertised context and usable context are different things. How to tell which window actually holds up.
· 9 min read
Expert Routing in MoE: How a Token Picks Its Path
The router decides which experts see each token, and that one small network shapes quality, throughput and why identical prompts can behave differently.
· 9 min read
Exponential Backoff That Works on LLM APIs
The retry algorithm in detail: full versus decorrelated jitter, deadline propagation, idempotency, what to classify as retryable, and how to test it before production does.
· 9 min read
Fallback Model Selection: Choosing Your Second Model Well
A fallback that behaves nothing like your primary turns an outage into a quality incident. How to pick a second model and prove it works.
· 9 min read
Few-Shot Example Management: Curation Beats Quantity
Few-shot examples decay, contradict each other and leak into output. How to choose them, order them, keep them in sync with your schema and know when to drop them.
· 9 min read
FinOps for AI Teams: What Transfers From Cloud and What Does Not
Cloud FinOps practice mostly transfers to LLM spend, but rightsizing and reserved capacity do not. What to keep, what to drop, and what to instrument first.
· 9 min readReady to try it?
Every model behind one key. Start free and upgrade when it sticks.