Tech AI News - 테카이

AI Glossary

Know Before You Use

20 posts

15. Why Granting AI Agents Broad Permissions Is Dangerous — Blast Radius

When an AI agent is given broad permissions ranging from sending emails to deleting files, a single small error can escalate into a major incident. This piece examines why, through the concepts of blast radius and least agency, and lays out design principles for adding confirmation steps around irreversible actions.

Know Before You Use· 5 min

14. Why Relying on a Single LLM API Comes Back to Bite You Later

Optimizing your prompts and code around a single LLM API means that price changes, model deprecations, and prompt incompatibility can all hit you with switching costs at once. Here are the principles for keeping a migration path open through a unified call layer and a maintained eval set.

Know Before You Use· 5 min

11. What Happens When You Cite AI-Fabricated Case Law As-Is

Why do lawyers keep getting sanctioned for filing fake case citations with courts, even knowing about AI hallucination? The line courts draw isn't about using AI — it's about failing to verify the result, a principle that applies equally to citations in academic papers and news articles.

Know Before You Use· 6 min

On-Device AI — AI That Runs Without the Internet

What on-device AI, where a smartphone's or laptop's own chip handles AI computation without an internet connection, actually is, how it differs from cloud AI, and how practical it is, based on 2026 chipset specs and market data.

Know Before You Use· 5 min

Benchmarks — Can You Trust "#1 in AI Performance"?

A number-one benchmark score may come from a model that saw the exam in advance, or from an exam unrelated to your work. Through the 2026 retirement of SWE-bench and the LM Arena controversy, here are six principles for reading scores.

Know Before You Use· 7 min

Parameters — 70B, 405B… What Do These Numbers Mean?

The B after a model's name is not a report card; it is closer to a hardware requirements sheet. Read this number as a performance ranking and your model choice is almost guaranteed to be wrong.

Know Before You Use· 10 min