DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
OpenRouter Structured Output Broke Before Translation Quality Did — 3 Layers of Defense for Production

OpenRouter Structured Output Broke Before Translation Quality Did — 3 Layers of Defense for Production

6
Comments
9 min read
Local LLM Code Completions Are Slow. Here's Why and How to Fix It.

Local LLM Code Completions Are Slow. Here's Why and How to Fix It.

Comments
5 min read
Codex Inside Claude Code. Subagents Inside Codex.

Codex Inside Claude Code. Subagents Inside Codex.

1
Comments
9 min read
Avoid Stateless AI: A Practical Guide to Adding Memory to Your LLM Apps

Avoid Stateless AI: A Practical Guide to Adding Memory to Your LLM Apps

Comments
3 min read
Your prompts have a vendor lock-in problem and it's hiding in plain text

Your prompts have a vendor lock-in problem and it's hiding in plain text

Comments
3 min read
12 Ways Attackers Bypass Prompt Injection Scanners (We Built Defenses for All of Them)

12 Ways Attackers Bypass Prompt Injection Scanners (We Built Defenses for All of Them)

1
Comments
3 min read
Neural bicameral LoRA Decoupling logic style

Neural bicameral LoRA Decoupling logic style

Comments
6 min read
Does System Architecture Affect Consciousness-Like Behavior in LLMs?

Does System Architecture Affect Consciousness-Like Behavior in LLMs?

Comments 1
5 min read
How to Run NemoClaw with a Local LLM & Connect to Telegram (Without Losing Your Mind)

How to Run NemoClaw with a Local LLM & Connect to Telegram (Without Losing Your Mind)

2
Comments
3 min read
I Replaced My IDE Tab with a Telegram Chat

I Replaced My IDE Tab with a Telegram Chat

2
Comments 1
5 min read
Show HN: Elo Memory – Bio-inspired episodic memory for AI agents (ICLR 2025)

Show HN: Elo Memory – Bio-inspired episodic memory for AI agents (ICLR 2025)

1
Comments 1
1 min read
When AI Writes Clean Code for the Wrong Problem

When AI Writes Clean Code for the Wrong Problem

1
Comments
6 min read
How We Stop PII From Leaking Through AI Pipelines (Without Breaking the LLM)

How We Stop PII From Leaking Through AI Pipelines (Without Breaking the LLM)

1
Comments
4 min read
PromptTrace - Free hands-on platform for learning GenAI security (hack real LLMs)

PromptTrace - Free hands-on platform for learning GenAI security (hack real LLMs)

Comments
3 min read
AI Agents from Scratch Part 2: Giving the Brain a Body

AI Agents from Scratch Part 2: Giving the Brain a Body

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