DEV Community

[画像:yuer profile picture]

yuer

Yuer — Independent AI Systems Architect Building the Expression-Driven Cognitive Architecture (EDCA OS): a deterministic, auditable execution layer for LLMs. Focused on: deterministic RAG & reproduc

Joined on Nov 20, 2025 lipxtk@gmail.com

Badges

Writing Debut

Writing Debut badge

Writing Debut

Awarded for writing and sharing your first DEV post! Continue sharing your work to earn the 4 Week Writing Streak Badge.

37 posts published

1 comment written

1 tag followed

A Deterministic PC Builder That Refuses to Guess — Powered by Algolia Agent Studio

A Deterministic PC Builder That Refuses to Guess — Powered by Algolia Agent Studio

#devchallenge #algoliachallenge #ai #agents

3 min read

Want to connect with yuer?

Create an account to connect with yuer. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in

Alignment Protocol v3.0: Defining Legal Admission Semantics for AI-Controlled Systems

Alignment Protocol v3.0: Defining Legal Admission Semantics for AI-Controlled Systems

#ai #architecture #security

1 min read

EDCA Admission Protocols: Introducing an Explicit Admission Layer for AI Systems

EDCA Admission Protocols: Introducing an Explicit Admission Layer for AI Systems

#ai #architecture #security #systemdesign

2 min read

When Factor Libraries Meet Real-World Execution Constraints

When Factor Libraries Meet Real-World Execution Constraints

#architecture #dataengineering #softwareengineering

2 min read

Building a Fail-Closed Investment Risk Gate with Yuer DSL

Building a Fail-Closed Investment Risk Gate with Yuer DSL

#architecture #security #testing

3 min read

LLMs Are Becoming an Explanation Layer And Our Interaction Defaults Are Breaking Systems

LLMs Are Becoming an Explanation Layer And Our Interaction Defaults Are Breaking Systems

#discuss #ai #llm #ux

3 min read

Why LLMs Break in Production (and Why It’s Not a Model Problem)

Why LLMs Break in Production (and Why It’s Not a Model Problem)

#llm #softwareengineering #systemdesign

3 min read

Controllable AI Must Sit in the Control Plane — Otherwise It Shouldn’t Exist

Controllable AI Must Sit in the Control Plane — Otherwise It Shouldn’t Exist

#ai #architecture #systemdesign

2 min read

When Community AI Breaks, It’s Rarely the Model

When Community AI Breaks, It’s Rarely the Model

#ai #community #data #systemdesign

3 min read

A Fail-Closed Gate for Rust AI Assistants

A Fail-Closed Gate for Rust AI Assistants

#discuss #codequality #rust #ai

2 min read

Controllable AI: A Runtime Legitimacy Layer for AI Governance

Controllable AI: A Runtime Legitimacy Layer for AI Governance

#architecture #agents #llm #ai

3 min read

Stop Giving AI the Steering Wheel

Stop Giving AI the Steering Wheel

#architecture #agents #security #ai

2 min read

Your AI Agent Isn’t Unsafe — It’s Unstoppable (And That’s the Problem)

Your AI Agent Isn’t Unsafe — It’s Unstoppable (And That’s the Problem)

2 min read

AI Systems That Can’t Say "No" Are Not Production-Ready

AI Systems That Can’t Say "No" Are Not Production-Ready

#ai #security #systemdesign

2 min read

Why AI Agents Break in Production (And Why It’s Not a Prompt Problem)

Why AI Agents Break in Production (And Why It’s Not a Prompt Problem)

#agents #ai #architecture

5 min read

Why Interruptible Voice AI Is a Systems Problem (Not an AI Problem)

Why Interruptible Voice AI Is a Systems Problem (Not an AI Problem)

#discuss #systemdesign #architecture #ai

2 min read

Why Distributed Query Engines Always Accumulate Complexity in the Execution Layer

Why Distributed Query Engines Always Accumulate Complexity in the Execution Layer

#architecture #database #rust

3 min read

Starting a Distributed Query Engine with a Minimal Rust Execution POC

Starting a Distributed Query Engine with a Minimal Rust Execution POC

3 min read

Why Post-Hoc Moderation Fails in Real-Time Systems

Why Post-Hoc Moderation Fails in Real-Time Systems

#architecture #security #systemdesign

4 min read

I Stopped Automating ecisions with AI — and Designed a Better Collaboration Instead

I Stopped Automating ecisions with AI — and Designed a Better Collaboration Instead

#discuss #design #automation #ai

4 min read

Prompt Engineering Is Fragile — Human–AI Collaboration Is the Real Interface

Prompt Engineering Is Fragile — Human–AI Collaboration Is the Real Interface

#discuss #llm #promptengineering #ai

2 min read

Powerful LLMs Are Not the Problem — Using Them "Raw" Is A systems-engineering view for builders

Powerful LLMs Are Not the Problem — Using Them "Raw" Is A systems-engineering view for builders

#softwareengineering #llm #ai #architecture

5 min read

The GPT Client Is Becoming the Runtime for Human–AI Collaboration

The GPT Client Is Becoming the Runtime for Human–AI Collaboration

#ai #architecture #llm

3 min read

AI decision systems break without strategy stability

AI decision systems break without strategy stability

#ai #architecture #llm

2 min read

Using a Single GPT Client as a Language Runtime (No API, No Agents)

Using a Single GPT Client as a Language Runtime (No API, No Agents)

#chatgpt #llm #architecture #ai

2 min read

Controllable AI: Why Enterprise AI Fails at Behavior, Not Models

Controllable AI: Why Enterprise AI Fails at Behavior, Not Models

#ai #machinelearning #architecture #enterprisetech

6 min read

AI Is Powerful — But Most of Us Are Still Using It the Wrong Way

AI Is Powerful — But Most of Us Are Still Using It the Wrong Way

2 min read

If the Same Input Gives Different Results, It’s Not a Decision System

If the Same Input Gives Different Results, It’s Not a Decision System

#discuss #ai #systemdesign

2 min read

Using GPT as a Code Auditor (Not a Code Generator)

Using GPT as a Code Auditor (Not a Code Generator)

#ai #security #testing

2 min read

Chat-based AI Breaks Down for Long-Running Work

Chat-based AI Breaks Down for Long-Running Work

#discuss #llm #ai #productivity

2 min read

You Don’t Need RAG to Build a Domain Sentiment Engine — A Single LLM + JSON Works

You Don’t Need RAG to Build a Domain Sentiment Engine — A Single LLM + JSON Works

#ai #machinelearning #llm #nlp

2 min read

A RAG-Free Technique That Makes LLM Outputs Stable, Predictable, and Auditable

A RAG-Free Technique That Makes LLM Outputs Stable, Predictable, and Auditable

#rag #llm #architecture #ai

2 min read

I Turned ChatGPT Web Into a Controllable Risk Engine — No Code, No API, No RAG

I Turned ChatGPT Web Into a Controllable Risk Engine — No Code, No API, No RAG

3 min read

Turning ChatGPT into a Deterministic Flight-Risk Runtime (FRR Demo + GitHub Repo)

Turning ChatGPT into a Deterministic Flight-Risk Runtime (FRR Demo + GitHub Repo)

2 min read

Why RAG and Agent Systems Are Unstable — A Minimal Deterministic Planner POC

Why RAG and Agent Systems Are Unstable — A Minimal Deterministic Planner POC

#agents #rag #architecture #llm

2 min read

Fixing Identity Drift in AI Image Generation with a Deterministic Constraint Layer (Minimal PoC Inside)

Fixing Identity Drift in AI Image Generation with a Deterministic Constraint Layer (Minimal PoC Inside)

#algorithms #ai #deeplearning #machinelearning

2 min read

Deterministic RAG: A Drop-in Replacement for GraphRAG’s Unstable Planning

Deterministic RAG: A Drop-in Replacement for GraphRAG’s Unstable Planning

#architecture #llm #rag

3 min read

loading...