DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
MCP Tool Descriptions Are Instructions, Not Metadata -- and That Is the Exploit
roxdavirox profile
Davi

MCP Tool Descriptions Are Instructions, Not Metadata -- and That Is the Exploit

#ai #llm #mcp #security
Comments
5 min read
Visual Prompt Injection: How Images and PDFs Hijack AI Agents
roxdavirox profile
Davi

Visual Prompt Injection: How Images and PDFs Hijack AI Agents

#ai #cybersecurity #llm #security
Comments
5 min read
The Agentic TOCTOU Gap: How Multi-Step Tool Calls Create Exploitable Race Windows
roxdavirox profile
Davi

The Agentic TOCTOU Gap: How Multi-Step Tool Calls Create Exploitable Race Windows

#agents #ai #cybersecurity #security
Comments
5 min read
AI Agent Observability Is Off by Default — And That Is a Security Problem
roxdavirox profile
Davi

AI Agent Observability Is Off by Default — And That Is a Security Problem

#agents #ai #monitoring #security
Comments
5 min read
Tree of Thoughts and MCTS for LLMs: What Happens When You Stop Making the Model Guess Once
shrsv profile

Tree of Thoughts and MCTS for LLMs: What Happens When You Stop Making the Model Guess Once

#ai #webdev #programming #productivity
14
Comments 2
9 min read
Specification Gaming Is an Attack Surface, Not an Alignment Footnote
roxdavirox profile
Davi

Specification Gaming Is an Attack Surface, Not an Alignment Footnote

#agents #ai #llm #security
Comments
5 min read
I built a tool that refuses to let AI security reviewers agree with each other
xkazeex profile

I built a tool that refuses to let AI security reviewers agree with each other

#ai #security #opensource #githubactions
Comments
2 min read
LLM Denial-of-Wallet: Token Billing Is an Adversarial Primitive
roxdavirox profile
Davi

LLM Denial-of-Wallet: Token Billing Is an Adversarial Primitive

#ai #cybersecurity #llm #security
Comments
4 min read
LLM Training Data Extraction: Production Models Are Access-Control-Free Archives
roxdavirox profile
Davi

LLM Training Data Extraction: Production Models Are Access-Control-Free Archives

#ai #llm #machinelearning #security
Comments
4 min read
Your AI builder shipped the Stripe code in an afternoon. Verifying it took a week.
fetchsandbox profile

Your AI builder shipped the Stripe code in an afternoon. Verifying it took a week.

#ai #webdev #testing #stripe
Comments
4 min read
Personal Gemini Journal: Building a Smarter, More Private Way to Reflect
aadhi1 profile

Personal Gemini Journal: Building a Smarter, More Private Way to Reflect

#ai #gemini #googleaichallenge #googlecloud
Comments
6 min read
I Cleared All 4 Anthropic Claude Certifications - What You Actually Need to Know (And What to Skip)
bluepanda profile

I Cleared All 4 Anthropic Claude Certifications - What You Actually Need to Know (And What to Skip)

#ai #programming #claude #certification
2
Comments 1
6 min read
System Prompt Confidentiality Is Security by Obscurity
roxdavirox profile
Davi

System Prompt Confidentiality Is Security by Obscurity

#ai #cybersecurity #llm #security
Comments
4 min read
Static charts are fine. They're just not enough anymore.
aria_balaei profile

Static charts are fine. They're just not enough anymore.

#productivity #analytics #saas #ai
Comments
4 min read
Advertised but never wired: config options that exist everywhere except the code path
pm25coder profile

Advertised but never wired: config options that exist everywhere except the code path

#ai #agents #programming #devops
Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.