DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
We Measured LLM Prompt Caching in Production — Same Prompt, 0% to 91% Hit Rates

We Measured LLM Prompt Caching in Production — Same Prompt, 0% to 91% Hit Rates

Comments
5 min read
Your Scaffold Will Be Gamed

Your Scaffold Will Be Gamed

1
Comments
6 min read
Stop Guessing: Guaranteed Structured Output from LLMs in Node.js

Stop Guessing: Guaranteed Structured Output from LLMs in Node.js

3
Comments 2
3 min read
What Is Lua AI? A Developer's Guide to Building AI Agents

What Is Lua AI? A Developer's Guide to Building AI Agents

2
Comments
3 min read
I stopped prompting my agent. Now I design the loop that prompts it.

I stopped prompting my agent. Now I design the loop that prompts it.

8
Comments 3
5 min read
Stop hand-parsing LLM JSON: structured outputs with pydantic-ai

Stop hand-parsing LLM JSON: structured outputs with pydantic-ai

2
Comments 1
2 min read
The End of AI "Slop"? How Google is Using LoRA and LLMs to Fight Coordinated Synthetic Spam

The End of AI "Slop"? How Google is Using LoRA and LLMs to Fight Coordinated Synthetic Spam

1
Comments
5 min read
/align v0.8 — personal evals for Claude Code, maintained by an LLM agent

/align v0.8 — personal evals for Claude Code, maintained by an LLM agent

Comments 1
4 min read
OWASP LLM Top 10 in Production: How I Audited My TypeScript Agent Pipeline Against All 10 Risks — and What I Found

OWASP LLM Top 10 in Production: How I Audited My TypeScript Agent Pipeline Against All 10 Risks — and What I Found

1
Comments
9 min read
Notes: Memory, Context, and Large Language Models (LLMs)

Notes: Memory, Context, and Large Language Models (LLMs)

4
Comments 1
9 min read
OpenAI Responses API vs Custom RAG: Cost, Latency and Control in 2026

OpenAI Responses API vs Custom RAG: Cost, Latency and Control in 2026

Comments
4 min read
Tracking token usage across OpenAI, Anthropic, and Gemini: every streaming gotcha I hit

Tracking token usage across OpenAI, Anthropic, and Gemini: every streaming gotcha I hit

Comments 1
5 min read
Five tool-calling patterns that separate hobby AI agents from production ones

Five tool-calling patterns that separate hobby AI agents from production ones

1
Comments 2
6 min read
Does Human-in-the-Loop Actually Improve AI Safety?

Does Human-in-the-Loop Actually Improve AI Safety?

1
Comments 1
7 min read
Stale RAG vs. expensive RAG: how to cache RAG context without serving outdated answers

Stale RAG vs. expensive RAG: how to cache RAG context without serving outdated answers

2
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.