#deep-dive
Every post tagged "deep-dive".
107 posts · showing 101–107
-
The Demo-to-Production Gap Is an Evaluation Gap
Demos answer "can it?" Deployments ask "how often, across everything real users send, when the tools misbehave?" Five variants of your demo scenario will tell you more than the demo did.
-
Indirect Prompt Injection: When the Tool Result Is the Attack
The attack doesn't come from your user — it comes from the page, ticket, or document your agent fetched. Three conditions have to hold for it to work, and breaking any one is an architectural choice, not a prompt.
-
The Skill Agents Erode Fastest: Reading Unfamiliar Code
Delegating code traversal is pure gain. Delegating comprehension means not having the model — and review quality is bounded by the model you don't have.
-
Agent Adoption Stalls at Trust, Not Capability
An agent whose errors cluster somewhere describable beats a more accurate one whose errors are scattered. Ask your users when they double-check its work — the answer is your real roadmap.
-
Reflection Loops Are Not Free: When Self-Critique Makes the Output Worse
A critique step can only catch what was already derivable from the context — and asked to find problems, a model will find them in passages that were fine. Here's when the pattern earns its doubled token bill.
-
The Confused Deputy in Your Agent: When the Tool Trusts the Model Too Much
Your refund tool checks whether the agent is allowed to issue refunds. Nothing checks whether the customer asking for one is entitled to it — and that gap opens without any jailbreak at all.
-
Why Your Agent Forgets Step 2 by Step 7 — And Four Ways to Keep the Thread
Agents rarely fail because they reason badly — they fail because the original instruction gets buried under accumulated tool output. Here's how to tell displacement from dilution, and four fixes that keep the thread intact.