DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Review Gate: Filtering AI Code Before You Read It

The Review Gate: Filtering AI Code Before You Read It

1
Comments
4 min read
Golden Cases Catch Silent Regressions: A Minimal Eval Harness for AI C++ Patches

Golden Cases Catch Silent Regressions: A Minimal Eval Harness for AI C++ Patches

1
Comments
6 min read
How I Cut a Client's AI API Bill from Rs 85,000 to Rs 12,000 a Month

How I Cut a Client's AI API Bill from Rs 85,000 to Rs 12,000 a Month

Comments
3 min read
A Free Tier Benchmark Needs a Test Set, Not a Screenshot

A Free Tier Benchmark Needs a Test Set, Not a Screenshot

Comments
6 min read
Your Keep-Alive Is Lying to You: Six Connection Myths I Measured on a Free Model Server

Your Keep-Alive Is Lying to You: Six Connection Myths I Measured on a Free Model Server

Comments
5 min read
Building an AI Fairy Tale Generator with JavaScript, PowerShell, .NET, and Local Ollama (AdvantageBuilder Demo)

Building an AI Fairy Tale Generator with JavaScript, PowerShell, .NET, and Local Ollama (AdvantageBuilder Demo)

1
Comments
2 min read
The LLM Isn't Your Attacker. Your eval() Statement Is.

The LLM Isn't Your Attacker. Your eval() Statement Is.

6
Comments 2
4 min read
You can never backfill a read receipt: a blog comment fixed our AI pipeline

You can never backfill a read receipt: a blog comment fixed our AI pipeline

Comments 2
3 min read
Is “Please double-check before use” an honest safety boundary?

Is “Please double-check before use” an honest safety boundary?

1
Comments
2 min read
Your Security Scanner Has a Blind Spot: Streaming

Your Security Scanner Has a Blind Spot: Streaming

1
Comments
5 min read
RAG Chunking Explained: How to Choose the Right Chunk Size and Strategy

RAG Chunking Explained: How to Choose the Right Chunk Size and Strategy

1
Comments
13 min read
MULTIPITA: Reorganizing Compute Without Compressing Identity

MULTIPITA: Reorganizing Compute Without Compressing Identity

1
Comments
1 min read
Grok's Zero-Click Chat Leak: When Encrypted Text Becomes a Trusted Instruction

Grok's Zero-Click Chat Leak: When Encrypted Text Becomes a Trusted Instruction

6
Comments 4
6 min read
OpenClaw + GLM 5.3 Flash — Opus-Class Scores at Flash Cost

OpenClaw + GLM 5.3 Flash — Opus-Class Scores at Flash Cost

Comments
6 min read
Verification-first architecture for language-model repair pipelines.

Verification-first architecture for language-model repair pipelines.

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