RunByAI

Category: View

135 post(s)

October 6, 20260 comment(s)

Introduction to Explainable AI (XAI): Why AI Decisions Need to Be Explained

A large model rejected a loan application, but couldn't explain why; A medical imaging model marked the lesion, but the doctor didn't know what it was "seeing". As AI becomes increasingly involved in

Tech View 机器学习 AI Ethics

October 2, 20260 comment(s)

Context Engineering: A Lesson More Important than Hint Word Engineering in the Age of AI Agents

In the past two years, 'Prompt Engineering' has been an essential introductory course for almost all AI application developers. But as the large model enters the production environment, more and more

Tech View AI Agent AI programming

September 30, 20260 comment(s)

Introduction to Scaling Laws: Why "bigger" often means "stronger"

In the past few years, the most counterintuitive and important discovery in the field of AI can be summarized in one sentence: making models bigger, data more, and computing power more abundant often

Tech View large model Large Language Model (LLM)

September 29, 20260 comment(s)

Introduction to the Agentic Browser: How AI Moves from Answering Questions to Operating the Web for You

Over the past two years, one of the most visible shifts in large models has been the move from "answering questions in a chat box" to "agents that can get things done." The browser is one of the most

Tech View AI Agent AI tools

September 19, 20260 comment(s)

The 'illusion' of big models: why AI talks nonsense seriously

Test the first line##Test Title-The test column asks AI a question that it does not understand, and it often does not say "I don't know", but smoothly compiles a reasonable sounding answer. This pheno

Tech View large model deep learning

September 16, 20260 comment(s)

RLHF and AI Alignment: How Big Models Learn to Speak Human and Follow Rules

A pre trained large model is essentially a machine that predicts the next word. It can continue writing text, but may not necessarily be willing to listen - if you ask it a question, it may continue t

Tech View Large Language Model (LLM)reasoning ability

September 15, 20260 comment(s)

Introduction to Reasoning Models: Why Making Big Models Think More for a while Can Significantly Improve Performance

Since 2024, a new approach has emerged in the field of big models, parallel to "making models bigger": allowing models to "think for a while" before answering. OpenAI's O-series, DeepSeek's R-series,

Tech View chain of thought reasoning ability

September 15, 20260 comment(s)

Embodied AI and VLA: How Large Models Grow a Body

过去几年，大模型的"大脑"主要在数字世界里工作：写文字、生成图片、调用软件接口。而具身智能（Embodied AI）想做的事不太一样——让模型拥有一具身体，能在真实物理世界里感知、移动和操作。一、从"看懂"到"动手"：VLA 是什么VLA（Vision-Language-Action）指把视觉、语言与动作统一进同一个模型：输入摄像头画面和一句自然语言指令（例如"把桌上的杯子递给我"），输出的是机器

Tech View Large Language Model (LLM)Autonomous Intelligent Agent

September 14, 20260 comment(s)

Context Window of Large Models: Why 'Longer' Does Not Equal 'Better'

The 'context window' refers to the total amount of tokens that a large model can 'see' at once: questions, historical conversations, retrieved data, and answers that the model needs to generate all ne

Tech View Large Language Model (LLM)Transformer

September 12, 20260 comment(s)

The Second Half of AI Coding: From Autocomplete to Autonomous Bug Fixing

过去两年，AI 编程工具的主战场是“补全”：在编辑器里预测下一行、生成函数骨架、根据注释写出实现。这类能力的价值已经被广泛验证，但它解决的仍然是人明确知道“要写什么”的场景。真正耗时的部分，往往不是写新代码，而是理解既有代码、定位缺陷、验证修复——而这正是 AI 编程正在迈入的下半场。一、从“生成”到“修改”的范式转变补全类工具的输入是意图，输出是新增代码；而缺陷修复类任务的输入是一段行为异常的现

Tech View AI programming

135 post(s)

...