DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Nobody audits their OpenAI invoice

Nobody audits their OpenAI invoice

3
Comments 4
5 min read
Compact Design: a JSON language models can write and Figma can import

Compact Design: a JSON language models can write and Figma can import

Comments
3 min read
RAG vs. Direct Context: I Tested Both on Real Documents, Here's What Broke

RAG vs. Direct Context: I Tested Both on Real Documents, Here's What Broke

Comments
5 min read
Your LLM gateway takes a cut. Seventeen lines of Python tell you how big.

Your LLM gateway takes a cut. Seventeen lines of Python tell you how big.

Comments
4 min read
Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit

Stealing Reasoning Traces from LLM APIs: How It Works and What to Audit

Comments 1
8 min read
Support Catalog Backfill: Moderate Existing Posts and Comments in a Node.js Bulk Job

Support Catalog Backfill: Moderate Existing Posts and Comments in a Node.js Bulk Job

Comments
6 min read
LLM Model Selection Matrix: Pick the Cheapest Reliable Model for Each Feature

LLM Model Selection Matrix: Pick the Cheapest Reliable Model for Each Feature

1
Comments
9 min read
Are You Benchmarking the Model—or the Harness?

Are You Benchmarking the Model—or the Harness?

1
Comments
8 min read
I Gave DeepSeek a Token Limit. It Ignored Me.

I Gave DeepSeek a Token Limit. It Ignored Me.

2
Comments 2
7 min read
loveyourclanker.org

loveyourclanker.org

Comments
1 min read
I filled my agent's wiki with contradictions. It never gave a wrong answer.

I filled my agent's wiki with contradictions. It never gave a wrong answer.

Comments 1
5 min read
Agent OS: tratar as instruções de um agente como sistema, não como prompt

Agent OS: tratar as instruções de um agente como sistema, não como prompt

Comments 1
6 min read
Verify AI Token Cost Cuts with MgntUtils Stacktrace Filtering on your own data — Before You Touch Production

Verify AI Token Cost Cuts with MgntUtils Stacktrace Filtering on your own data — Before You Touch Production

Comments
3 min read
Local vs Hosted LLMs: The Decision Framework

Local vs Hosted LLMs: The Decision Framework

Comments
10 min read
The Same Claude Model Gives You 60 Days' Notice on One Platform and 184 on Another

The Same Claude Model Gives You 60 Days' Notice on One Platform and 184 on Another

Comments
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.