Guidescurl Recipes for LLM APIs: Debug Before You Write Code
A working set of curl commands for OpenAI-compatible endpoints: streaming, timing, tool calls, error bodies, and building JSON safely with jq.
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.
Guides
GuidesCursor Setup Guide: Pointing It at Your Own Endpoint
How to run Cursor against a custom OpenAI-compatible base URL, which features stop using your key, and how to tell whether the override took effect.
Read
FundamentalsData Contamination in Training: Why Scores Overstate Skill
How benchmark data leaks into training sets, why it is hard to prove, and what a contaminated score actually costs you when you pick a model for real work.
Read
AI AgentsDebugging a Stuck Agent: A Triage Runbook
Stuck is four different failures with four different fixes. How to tell hung from looping from stalled from quietly truncated, and what to do about each one.
Read
ModelsDeepSeek V4 Flash vs MiniMax M3: Cheapest Against Multimodal
Two budget models with 1M context. One is cheaper and text-only under MIT, the other sees images. The choice is almost entirely about input type.
Read
ModelsDeepSeek V4 Flash vs Qwen 3.6: Rent Cheap or Own It
A 13B-active MoE at fourteen cents per million tokens against a dense 27B you can run yourself. The crossover point is lower than most teams assume.
Read
ModelsDeepSeek V4 Flash: 1M Context at 13B Active Parameters
The cheap half of the DeepSeek V4 family keeps the million-token window and drops active parameters to 13B. What that trade buys, and where it stops working.
Read
ModelsDeepSeek V4 Pro vs Qwen 3.6: 1.6T or 27B, for 3 Points
V4 Pro reports 80.6 percent on SWE-bench Verified, Qwen 3.6 27B reports 77.2. One is sixty times larger. What that tells you about model size in 2026.
Read
ModelsDeepSeek V4 Pro vs V4 Flash: Same Window, Different Brain
Both ship 1M context and an MIT licence. Pro activates 49B parameters per token, Flash 13B. Where that single difference decides which one you should run.
ReadModelsDense vs Mixture-of-Experts: Which You Can Actually Run
MoE models are cheap to compute and expensive to hold. Dense models are the reverse. The architecture decides your deployment more than your benchmark scores.
Read
AI AgentsDependency-Aware Planning: Ordering Work That Blocks
Most agent plans are flat lists executed top to bottom. Modelling dependencies instead unlocks parallelism, better retries and honest progress reporting.
Read
Cost & PricingDesigning an AI Spend Dashboard People Actually Read
Most LLM cost dashboards show token counts nobody acts on. The four or five panels worth keeping, why unit cost beats totals, and how to avoid vanity metrics.
ReadShowing 97–108 of 404 articles