Skip to content

DEV Community

# llm

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

Apr 25

Why LLM Agents Fail: Four Mechanisms of Cognitive Decay and the Reasoning Harness Layer

#ai #llm #agents #architecture

13 min read

Cor E

May 19

Brazilian Lawyers Fined R$84,000 for Prompt Injection in Court — Here's What Caught Them (and What Didn't)

#security #ai #appsec #llm

5 min read

Machine coding Master

Apr 26

Stop Hand-Rolling AI Glue: Claude 4 MCP + Spring AI is the New Enterprise Standard

#java #ai #llm #systemdesign

2 min read

soy

Apr 25

Qwen3.6-27B vLLM 0.19 Benchmarks, GLM 5.1 Local Performance, & Multimodal WaTale

#ai #llm #selfhosted

4 min read

Cor E

Apr 26

Your AI Agent Is Reading Poisoned Web Pages (And You Don't Know It)

#ai #webdev #infosec #llm

4 min read

Apr 25

Why Your AI Agent Loses the Plot: Reasoning Decay and Attention Loss in Long-Running Tasks

#ai #llm #agents #programming

10 min read

Anti-prompts that make model failure visible

May 12

Prompting Is Not Magic. It Is Control.

#promptengineering #ai #security #llm

8 min read

Kazuma Horishita

Apr 25

Model Output Is Not Authority: Action Assurance for AI Agents

#ai #security #llm #architecture

7 min read

May 27

An AI Agent Wiped a Production Database in 9 Seconds. What Engineers Must Design Before Shipping.

#llm #agents #enterprise #aisafety

5 min read

REX

May 19

Moving Beyond My Go-To LLM: Is Anyone Using Anthropic's Mythos? 🤖

#ai #llm #developer #productivity

1 min read

Alan West

May 18

Why MTP doesn't speed up your llama.cpp inference (and how to actually fix it)

#llm #performance #machinelearning #gpu

5 min read

Marketing Coderslab

May 18

How LLMs Actually Work (And What That Means for Your Architecture Decisions)

#ai #machinelearning #llm #webdev

6 min read

Dmytro Poliakov

Apr 25

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

#ai #llm #deepseek #opensource

1 min read

YASHWANTH REDDY K

Apr 25

I built Geometric Breathing & Meditation app on VCA

#vibecodearena #hackerearth #llm #multimodelduel

4 min read

Apr 25

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

#ai #agents #deepseek #llm

3 min read

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