DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I scanned 220,000 MCP tool descriptions for prompt injection. The scare is overblown — but 1 in 4 servers touches your credentials.

I scanned 220,000 MCP tool descriptions for prompt injection. The scare is overblown — but 1 in 4 servers touches your credentials.

4
Comments 14
3 min read
The Eval Pyramid, Part I: Testing Systems That Don't Behave the Same Way Twice

The Eval Pyramid, Part I: Testing Systems That Don't Behave the Same Way Twice

Comments
9 min read
We hid codes in 7 social media posts and asked 5 AI assistants to find them

We hid codes in 7 social media posts and asked 5 AI assistants to find them

Comments
3 min read
Your agent's success rate barely moved. One tool's error rate tripled.

Your agent's success rate barely moved. One tool's error rate tripled.

Comments
5 min read
Why I removed the dedup from my coding agent

Why I removed the dedup from my coding agent

Comments
4 min read
The False Positive Wasn't a SQLite Quirk: It Reopened on Elasticsearch Too

The False Positive Wasn't a SQLite Quirk: It Reopened on Elasticsearch Too

Comments
7 min read
The Eval Pyramid, Part II: Measuring Agent Reliability with pass@k, pass^k, and Judges You Can Trust

The Eval Pyramid, Part II: Measuring Agent Reliability with pass@k, pass^k, and Judges You Can Trust

1
Comments 1
9 min read
How many tokens do your MCP tools cost? Measure any remote MCP server in ~60 lines of Python

How many tokens do your MCP tools cost? Measure any remote MCP server in ~60 lines of Python

Comments 1
4 min read
Your AI agrees with whoever asks: a two-pass pattern for decisions about people

Your AI agrees with whoever asks: a two-pass pattern for decisions about people

Comments 1
3 min read
AI Agent Framework Tool Schemas Compared: Only 5 of 14 Put Your Docstring Arg Descriptions in the Schema (Nov 2026)

AI Agent Framework Tool Schemas Compared: Only 5 of 14 Put Your Docstring Arg Descriptions in the Schema (Nov 2026)

Comments
7 min read
Built a lightweight local FastAPI proxy to catch HTTP 429s and fail over from Cloud -> Groq -> Local LLM

Built a lightweight local FastAPI proxy to catch HTTP 429s and fail over from Cloud -> Groq -> Local LLM

Comments
1 min read
Rent the taxi or buy the car: the break-even maths for running your own model

Rent the taxi or buy the car: the break-even maths for running your own model

Comments
4 min read
Gemini 4 Neon Costs More Per Token and Less Per Task

Gemini 4 Neon Costs More Per Token and Less Per Task

Comments
6 min read
Your RAG assistant got 7 of 10 right. The other 3 failed for different reasons

Your RAG assistant got 7 of 10 right. The other 3 failed for different reasons

Comments
4 min read
How I detect B2B buying intent in public developer forums with Python + an LLM

How I detect B2B buying intent in public developer forums with Python + an LLM

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