#intermediate
Every post tagged "intermediate".
223 posts · showing 101–110
-
Lock-In Risk in Agent Tooling, and How to Keep Optionality
The API call is trivially portable — the coupling forms in four other places, and the worst one isn't technical at all. One question tells you how exposed you are.
-
The Moat Isn't the Model — It's the Loop Around It
"The model isn't the moat" is now widely said and stops one step short. What compounds shares a property — it accumulates from watching real usage, which is why it's invisible from outside.
-
Will Open-Source Harnesses Eat Commercial Coding Tools?
The premise is right — the loop is a few hundred lines. The conclusion is too fast, because the loop isn't the product, and one of the real advantages is invisible from outside.
-
IDE Assistants vs Agent Harnesses: Different Products, Different Futures
They get discussed as one category and have opposite requirements on latency, context, failure cost, and model tier. One is commoditizing into a feature; the other's differentiators aren't AI capabilities at all.
-
If Intelligence Gets Cheap, What Becomes Scarce?
More useful than asking what gets cheap. Everything on the scarce list has one of two properties — and neither can be produced on demand, which is exactly why they stay scarce.
-
What Falling Inference Costs Change About Agent Design
Relaxed cost pressure mainly buys back the verification steps you declined. It doesn't rehabilitate filling the context or adding turns — those were quality problems wearing a cost disguise.
-
The Case for a Local-First Agent Stack
The cost argument for local-first is weak and the ideology one is worse. The case that holds is dependency control — and it comes with a permanent operational tax nobody budgets.
-
What Runs Locally Today and What Still Won't Soon
Local handles the steps; hosted handles the orchestration. The agent loop is the hardest thing to localize, because it stresses all three local constraints at once.
-
Will On-Device Intelligence Be Free? What the Economics Say
"Free" means three different things here. Two are plausible and already partly true; the third doesn't follow, because the frontier is defined by requiring the most compute.
-
How to Benchmark Models on Your Own Task
Public benchmarks tell you about a model, not about your system. Frozen tool responses, assertions written from the requirement, and four numbers instead of one — plus the shortcut when a full suite isn't happening.