DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Catch prompt injection (and leaked secrets) in your AI agent's outgoing messages

Catch prompt injection (and leaked secrets) in your AI agent's outgoing messages

Comments
3 min read
AI Agent Debugging Checklist: From Failed Run to Root Cause

AI Agent Debugging Checklist: From Failed Run to Root Cause

1
Comments
5 min read
When Your Background AI Agent Becomes a C2 Server

When Your Background AI Agent Becomes a C2 Server

2
Comments
4 min read
AgentDoG 1.5: Small Inline Guard Models for Agent Actions

AgentDoG 1.5: Small Inline Guard Models for Agent Actions

Comments
7 min read
Aggregate eval scores hid a 14-point regression in one user segment

Aggregate eval scores hid a 14-point regression in one user segment

Comments
4 min read
I streamed Mixtral 8x7B from NVMe on a $0.40/hour VM and got 3.32 tps, here's how

I streamed Mixtral 8x7B from NVMe on a $0.40/hour VM and got 3.32 tps, here's how

Comments
4 min read
Agent Base Definition: Why It Is Not a Prompt

Agent Base Definition: Why It Is Not a Prompt

Comments
20 min read
AITUNNEL vs Promptra: цены, документы, ИП vs ООО

AITUNNEL vs Promptra: цены, документы, ИП vs ООО

Comments
3 min read
I tried to break my own MCP prompt-injection detector. One class of attack walks straight through - and it isn't a bug.

I tried to break my own MCP prompt-injection detector. One class of attack walks straight through - and it isn't a bug.

3
Comments 2
6 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

1
Comments
5 min read
How I Built a Customer Support Auto-Responder with Confidence Scoring Using pydantic-ai and FastAPI

How I Built a Customer Support Auto-Responder with Confidence Scoring Using pydantic-ai and FastAPI

Comments 2
6 min read
Gemma 4 12B: Google's encoder-free multimodal AI now runs on a laptop

Gemma 4 12B: Google's encoder-free multimodal AI now runs on a laptop

1
Comments
2 min read
AIchain Pool: Parallel Calls Instead of Sequential

AIchain Pool: Parallel Calls Instead of Sequential

Comments 3
5 min read
Making LLM outputs auditable: the provider abstraction pattern

Making LLM outputs auditable: the provider abstraction pattern

Comments
5 min read
Best Local Coding LLM in 2026: Qwen2.5-Coder vs DeepSeek-Coder-V2 vs Codestral

Best Local Coding LLM in 2026: Qwen2.5-Coder vs DeepSeek-Coder-V2 vs Codestral

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