DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your AI Agent Trusts Everything It Reads — A Field Guide to Hijacking Claude, GPT, Gemini & Copilot

Splitting the lethal trifecta fixes it

Your AI Agent Trusts Everything It Reads — A Field Guide to Hijacking Claude, GPT, Gemini & Copilot

16
Comments 14
15 min read
I stopped sending JSON keys to my LLM 100 times. Here's what it saved (and where it didn't)

I stopped sending JSON keys to my LLM 100 times. Here's what it saved (and where it didn't)

Comments
5 min read
Why Hashing Tool Calls Won't Catch Your Agent's Loops

Why Hashing Tool Calls Won't Catch Your Agent's Loops

Comments
6 min read
A Practical Taxonomy of Prompt Injection: 11 Techniques and What Stops Each One

A Practical Taxonomy of Prompt Injection: 11 Techniques and What Stops Each One

Comments
5 min read
Your Agent Used 6% of Its Context Window and Still Lost a Third of Its Tool Output

Your Agent Used 6% of Its Context Window and Still Lost a Third of Its Tool Output

Comments
5 min read
What an AI coding agent actually costs per month (and 5 ways to cut it)

What an AI coding agent actually costs per month (and 5 ways to cut it)

Comments 1
5 min read
Stop Flattening Your PDFs: Document Intelligence and Structural Chunking for RAG and Agents

Stop Flattening Your PDFs: Document Intelligence and Structural Chunking for RAG and Agents

Comments
20 min read
I Built a Self-Hosted ChatGPT on My Laptop. Here's What Broke.

I Built a Self-Hosted ChatGPT on My Laptop. Here's What Broke.

Comments
9 min read
Your LLM's JSON passed the schema. It was still wrong.

Your LLM's JSON passed the schema. It was still wrong.

Comments
9 min read
Multi-agent consensus: how to verify the result

Multi-agent consensus: how to verify the result

Comments
4 min read
Hallucination Is a Design Problem, Not a Model Problem

Hallucination Is a Design Problem, Not a Model Problem

Comments
6 min read
What is AI red teaming? A practical guide for security teams

What is AI red teaming? A practical guide for security teams

Comments
8 min read
Your tool descriptions are prompts: how to write tools LLM agents actually use correctly

Your tool descriptions are prompts: how to write tools LLM agents actually use correctly

Comments
5 min read
We read 202,073 UK job adverts with an LLM: 1 in 6 from visa-sponsor employers rule out sponsorship

We read 202,073 UK job adverts with an LLM: 1 in 6 from visa-sponsor employers rule out sponsorship

Comments
2 min read
AI code review: what the papers and tools say, compared to my skill

AI code review: what the papers and tools say, compared to my skill

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