News & guides
Cursor 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.
· 8 min read
Data 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.
· 9 min read
Debugging 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.
· 9 min read
DeepSeek 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.
· 8 min read
DeepSeek 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.
· 9 min read
DeepSeek 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.
· 8 min read
DeepSeek 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.
· 9 min read
DeepSeek 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.
· 8 min readDense 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.
· 9 min read
Dependency-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.
· 9 min read
Designing 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.
· 11 min read
Detecting Agent Loops Before They Burn Your Budget
A stuck agent repeats the same failing action until something stops it. How to detect repetition cheaply and what to do once you have.
· 8 min readReady to try it?
Every model behind one key. Start free and upgrade when it sticks.