DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Model Output Is Not Authority: Action Assurance for AI Agents

Model Output Is Not Authority: Action Assurance for AI Agents

1
Comments
7 min read
Fixing the Missing think Tag Glitch When Running DeepSeek V3.2 GGUF on CPU

Fixing the Missing think Tag Glitch When Running DeepSeek V3.2 GGUF on CPU

Comments
1 min read
Why AI Coding Agents Waste 30% of Their Tokens — And How to Fix It

Why AI Coding Agents Waste 30% of Their Tokens — And How to Fix It

Comments 1
6 min read
I built Geometric Breathing & Meditation app on VCA

I built Geometric Breathing & Meditation app on VCA

Comments
4 min read
DeepSeek V4's Real Innovation Isn't Scale—It's Memory Architecture

DeepSeek V4's Real Innovation Isn't Scale—It's Memory Architecture

Comments
3 min read
Without google's transformers, there is no GPT-ishs

Without google's transformers, there is no GPT-ishs

Comments
6 min read
Claude Skills and SKILL.md for Developers: VS Code, JetBrains, Cursor

Claude Skills and SKILL.md for Developers: VS Code, JetBrains, Cursor

Comments
14 min read
How an AI Agent Ran Up a $47,000 Bill in 11 Days (And How to Stop It)

How an AI Agent Ran Up a $47,000 Bill in 11 Days (And How to Stop It)

1
Comments
3 min read
LLM Planning, AI Arguments, and Building Persistent Worlds

LLM Planning, AI Arguments, and Building Persistent Worlds

Comments
2 min read
I Built a Glossary of LLM Terms That Actually Explains What They Change in Production

I Built a Glossary of LLM Terms That Actually Explains What They Change in Production

Comments
1 min read
How to Fine-Tune Claude on Amazon Bedrock for Your Domain (Complete Guide with Code)

How to Fine-Tune Claude on Amazon Bedrock for Your Domain (Complete Guide with Code)

Comments
8 min read
Cancelled Claude AI Agent: My 4 Reasons For The Switch

Cancelled Claude AI Agent: My 4 Reasons For The Switch

Comments
6 min read
Platform-Neutral AI Tools Are the Safer Long-Term Bet

Platform-Neutral AI Tools Are the Safer Long-Term Bet

Comments
8 min read
LLM Wiki vs RAG: a different approach to team-chat memory

LLM Wiki vs RAG: a different approach to team-chat memory

1
Comments
8 min read
40 cents a day, three weeks of corrupted writes, zero alerts fired

40 cents a day, three weeks of corrupted writes, zero alerts fired

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