DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Our Recall Was 0.087 and the Model Was Innocent: How Domain-Scoped Replay Doubled It

Our Recall Was 0.087 and the Model Was Innocent: How Domain-Scoped Replay Doubled It

20
Comments 11
6 min read
AX-RAY & K-MYTHOS: Inside Korea's Consortium-Built Security-Specialized AI Foundation Model

AX-RAY & K-MYTHOS: Inside Korea's Consortium-Built Security-Specialized AI Foundation Model

1
Comments
4 min read
The AI thinks, the gate decides — how I made LLM code edits deterministic (and cut token usage 42 )

The AI thinks, the gate decides — how I made LLM code edits deterministic (and cut token usage 42 )

2
Comments 24
11 min read
From Basic RAG to Production Guardrails: 6 Progressive Levels Explained (with Live Interactive Demo)

From Basic RAG to Production Guardrails: 6 Progressive Levels Explained (with Live Interactive Demo)

4
Comments 3
11 min read
How to Test AI Agents Without Vendor Lock-in — Introducing ABS

How to Test AI Agents Without Vendor Lock-in — Introducing ABS

Comments
5 min read
Why Accuracy Is the Hardest Thing to Get Right When Training AI

Why Accuracy Is the Hardest Thing to Get Right When Training AI

Comments
3 min read
I pay an LLM to approve bad reviews

I pay an LLM to approve bad reviews

Comments 1
5 min read
EPIC Mode: A Blueprint for Stopping Agent Overthinking

EPIC Mode: A Blueprint for Stopping Agent Overthinking

Comments
2 min read
The Memory Limit That Didn't Kill Anything

The Memory Limit That Didn't Kill Anything

1
Comments
6 min read
6 ways MCP servers get pwned — and the code that stops each one

6 ways MCP servers get pwned — and the code that stops each one

Comments
3 min read
Designing a parser contract for AI output (not just a prompt)

Designing a parser contract for AI output (not just a prompt)

Comments
3 min read
What Breaks First When You Swap a Local Coding Model for a Free Hosted One? A Failure-Mode Probe Suite

What Breaks First When You Swap a Local Coding Model for a Free Hosted One? A Failure-Mode Probe Suite

Comments
5 min read
Meta Muse Glimmer-30B: How a Dense Local Model Is Rethinking On-Device Agentic AI

Meta Muse Glimmer-30B: How a Dense Local Model Is Rethinking On-Device Agentic AI

Comments
4 min read
My quality gate wasn't strict. It was dead.

My quality gate wasn't strict. It was dead.

Comments
4 min read
Hype Cycles Don't Ship My Code: How I Gate New LLMs with a Self-Written Eval Deck

Hype Cycles Don't Ship My Code: How I Gate New LLMs with a Self-Written Eval Deck

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