DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your AI agent just leaked an SSN, cost surged and your tests passed. Here's why.

Your AI agent just leaked an SSN, cost surged and your tests passed. Here's why.

Comments
3 min read
Finally, Private AI Characters That Can Run Offline

Finally, Private AI Characters That Can Run Offline

4
Comments
5 min read
One Open Source Project a Day (No. 65): OpenHuman - A Local-First Personal AI Super Intelligence That Actually Knows You

One Open Source Project a Day (No. 65): OpenHuman - A Local-First Personal AI Super Intelligence That Actually Knows You

2
Comments
7 min read
Llama.cpp Tensor Parallelism, Gemma 4 Stability, & OmniVoice Local TTS

Llama.cpp Tensor Parallelism, Gemma 4 Stability, & OmniVoice Local TTS

Comments
3 min read
Is AI governance only about safety, or should it also control product behavior?

Is AI governance only about safety, or should it also control product behavior?

1
Comments 4
2 min read
[Project] My AI invented its own game, then lost at it — bio-inspired autonomous AI on a single PC

[Project] My AI invented its own game, then lost at it — bio-inspired autonomous AI on a single PC

Comments
2 min read
🛑 El Fin de la Era del "Wrapper": Arquitectura, Soberanía y el Verdadero Coste de la Agentic AI

🛑 El Fin de la Era del "Wrapper": Arquitectura, Soberanía y el Verdadero Coste de la Agentic AI

Comments
6 min read
Building Your Own "Google Maps for Codebases": A Practical Guide to Codebase Q&A with LLMs

Building Your Own "Google Maps for Codebases": A Practical Guide to Codebase Q&A with LLMs

Comments
6 min read
The Four Axes of AI Agent Efficiency: When to Use LLMs (And When Not To)

The Four Axes of AI Agent Efficiency: When to Use LLMs (And When Not To)

Comments
13 min read
Open Source AI Showdown 2026: Llama 4 vs Gemma 4 vs DeepSeek V4 vs GLM-5.1

Open Source AI Showdown 2026: Llama 4 vs Gemma 4 vs DeepSeek V4 vs GLM-5.1

Comments
2 min read
how to run qwen3.6-27b locally — the dense 27B that beats the 35B MoE on coding

how to run qwen3.6-27b locally — the dense 27B that beats the 35B MoE on coding

1
Comments
3 min read
I lost $14,502 to Claude Code in one month. Here's the autopsy.

I lost $14,502 to Claude Code in one month. Here's the autopsy.

1
Comments 2
8 min read
Docker Model Runner Replaced My Entire Local AI Setup

Docker Model Runner Replaced My Entire Local AI Setup

1
Comments
4 min read
I Scaled PHP Until It Broke. Three llama.cpp Patterns Saved It.

I Scaled PHP Until It Broke. Three llama.cpp Patterns Saved It.

Comments 1
10 min read
Why LLMs Will Never Become AGI: Teaching AI to Reflect Using Friston, Jung, and Julia

Why LLMs Will Never Become AGI: Teaching AI to Reflect Using Friston, Jung, and Julia

1
Comments 2
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.