DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Constraint Weakening in LLM Agent Workflows: Why \\\\\\\"Must\\\\\\\" Becomes \\\\\\\"Maybe\\\\\\\" Across Multi-Stage Pipelines

Constraint Weakening in LLM Agent Workflows: Why \\\\\\\"Must\\\\\\\" Becomes \\\\\\\"Maybe\\\\\\\" Across Multi-Stage Pipelines

Comments
6 min read
Why I Stopped Using Vector RAG for Coding Agents (And Used Git Markdown Instead)

Why I Stopped Using Vector RAG for Coding Agents (And Used Git Markdown Instead)

2
Comments 1
3 min read
MCP Describe Injection: Audit Tool Descriptions Like Code

MCP Describe Injection: Audit Tool Descriptions Like Code

1
Comments
4 min read
Local-First LLM Routing: A Decision Table for Latency, Secrets, and Offline Mode

Local-First LLM Routing: A Decision Table for Latency, Secrets, and Offline Mode

1
Comments
5 min read
Valence Sphere

Valence Sphere

Comments
2 min read
Picking Models as a Mac User

Picking Models as a Mac User

1
Comments
8 min read
Your local RAG isn't slow — it re-reads every document on every question

Your local RAG isn't slow — it re-reads every document on every question

Comments
9 min read
Agentic AI Security: Sandboxing LLM Tool Calls in Production

Agentic AI Security: Sandboxing LLM Tool Calls in Production

Comments
5 min read
LLM evals are a parameter sweep — use a parameter sweep tool

LLM evals are a parameter sweep — use a parameter sweep tool

Comments
9 min read
The MCP Vulnerability That Lives Between Servers, Not In One

The MCP Vulnerability That Lives Between Servers, Not In One

2
Comments 3
4 min read
I Reviewed 12 Free-Tier Integrations. The Same Six Myths Kept Appearing.

I Reviewed 12 Free-Tier Integrations. The Same Six Myths Kept Appearing.

Comments
4 min read
Free Tokens, Real Queues: Measure What Your LLM Calls Actually Cost

Free Tokens, Real Queues: Measure What Your LLM Calls Actually Cost

Comments
4 min read
LLM Evaluation for Software Engineers Without an ML Background: the 90+ Checks We Actually Run

LLM Evaluation for Software Engineers Without an ML Background: the 90+ Checks We Actually Run

Comments
10 min read
Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string

Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string

Comments 1
6 min read
A Decision Tree for Free-Tier AI Automation: Terms, Branches, Worked Leaves

A Decision Tree for Free-Tier AI Automation: Terms, Branches, Worked Leaves

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.