DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
SLMs vs. LLMs: When Smaller Wins

SLMs vs. LLMs: When Smaller Wins

1
Comments
8 min read
Generalist Reasoning vs Scoped Autonomy: Why Claude Opus 4.7 and OpenAI Codex Aren't Competing — and Why That Should Change How You Build

Generalist Reasoning vs Scoped Autonomy: Why Claude Opus 4.7 and OpenAI Codex Aren't Competing — and Why That Should Change How You Build

Comments
3 min read
Generalist Reasoning vs Scoped Autonomy: Why Claude Opus 4.7 and OpenAI Codex Aren't Competing — and Why That Should Change How You Build

Generalist Reasoning vs Scoped Autonomy: Why Claude Opus 4.7 and OpenAI Codex Aren't Competing — and Why That Should Change How You Build

Comments
3 min read
Stop Engineering Prompts: How an Eval-First Harness Let Us Ship 25 Algorithm Versions Autonomously

Stop Engineering Prompts: How an Eval-First Harness Let Us Ship 25 Algorithm Versions Autonomously

1
Comments 2
17 min read
Why AI feature rollouts fail before the model does

Why AI feature rollouts fail before the model does

Comments
8 min read
LLM Trace Storage Cost: Why Your S3 Bill Exploded, and 3 Fixes

LLM Trace Storage Cost: Why Your S3 Bill Exploded, and 3 Fixes

Comments 2
8 min read
OpenClaw Skills Ecosystem and Practical Production Picks

OpenClaw Skills Ecosystem and Practical Production Picks

Comments
11 min read
OpenClaw Plugins — Ecosystem Guide and Practical Picks

OpenClaw Plugins — Ecosystem Guide and Practical Picks

Comments
13 min read
7 Production RAG Mistakes I Made (And How to Fix Them)

7 Production RAG Mistakes I Made (And How to Fix Them)

1
Comments
5 min read
Two engines for AI slide decks: HTML output vs gpt-image-2 (and how we solved CJK rendering)

Two engines for AI slide decks: HTML output vs gpt-image-2 (and how we solved CJK rendering)

3
Comments
3 min read
Lakera Guard Was Acquired for $300M. Here Is the Free Alternative We Built for Developers.

Lakera Guard Was Acquired for $300M. Here Is the Free Alternative We Built for Developers.

Comments
4 min read
I Built an Offline AI Career Advisor Using Gemma 4 — Here's Exactly How It Works

I Built an Offline AI Career Advisor Using Gemma 4 — Here's Exactly How It Works

Comments
6 min read
MCP Security in 2026: How to Protect Your AI Agents from Prompt Injection

MCP Security in 2026: How to Protect Your AI Agents from Prompt Injection

Comments
7 min read
qwen2.5-coder is too slow for Claude Code on a Mac. Here's the fix.

qwen2.5-coder is too slow for Claude Code on a Mac. Here's the fix.

Comments 7
8 min read
Two architectures that didn't help small-model agent memory on a free T4

Two architectures that didn't help small-model agent memory on a free T4

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