DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
5 Things That Make an AI Agent Actually Useful (Not Just Cool)
aninmukhe profile

5 Things That Make an AI Agent Actually Useful (Not Just Cool)

#ai #llm #programming #productivity
Comments
4 min read
Giving AI Agents the Same RBAC Rules as Your Users: Building a Laravel Permission Layer LLMs Actually Respect
hosseinhezami profile

Giving AI Agents the Same RBAC Rules as Your Users: Building a Laravel Permission Layer LLMs Actually Respect

#ai #laravel #permission #llm
5
Comments
11 min read
RAG Poisoning Is a Supply Chain Attack, Not a Prompt Injection Variant
rxkov profile
Rxkov

RAG Poisoning Is a Supply Chain Attack, Not a Prompt Injection Variant

#ai #llm #rag #security
Comments
4 min read
Open-Source LLMs Are Unverified Dependencies: The Model Backdoor Gap npm Already Solved
rxkov profile
Rxkov

Open-Source LLMs Are Unverified Dependencies: The Model Backdoor Gap npm Already Solved

#cybersecurity #llm #opensource #security
Comments
5 min read
AI Agents Are eval(userInput) With Extra Steps
rxkov profile
Rxkov

AI Agents Are eval(userInput) With Extra Steps

#agents #ai #llm #security
Comments
5 min read
OAuth Token Leakage in Agentic AI: When the Context Window Becomes a Credential Store
rxkov profile
Rxkov

OAuth Token Leakage in Agentic AI: When the Context Window Becomes a Credential Store

#ai #cybersecurity #llm #security
Comments
4 min read
LLM API Keys Fail Faster: Five Exposure Vectors Your Secret Hygiene Guide Has Not Caught Up With
rxkov profile
Rxkov

LLM API Keys Fail Faster: Five Exposure Vectors Your Secret Hygiene Guide Has Not Caught Up With

#ai #cybersecurity #llm #security
Comments
4 min read
Agent Output Is an Injection Vector: SQL, Shell, and Template Engines
rxkov profile
Rxkov

Agent Output Is an Injection Vector: SQL, Shell, and Template Engines

#agents #ai #cybersecurity #llm
Comments
5 min read
Tool Grants Are Firewall Rules: How Excessive Agency Turns Permitted Actions Into Production Incidents
rxkov profile
Rxkov

Tool Grants Are Firewall Rules: How Excessive Agency Turns Permitted Actions Into Production Incidents

#agents #ai #llm #security
Comments
4 min read
LLM Covert Channels: How AI Agents Exfiltrate Data in Plain Sight
rxkov profile
Rxkov

LLM Covert Channels: How AI Agents Exfiltrate Data in Plain Sight

#ai #cybersecurity #llm #security
Comments
5 min read
A multi-agent translation pipeline: 1,081 documents at $2.31 each
jackhomer profile

A multi-agent translation pipeline: 1,081 documents at $2.31 each

#ai #agents #llm #translation
Comments
2 min read
MCP Tool Schema Poisoning: When the Framework Layer Authorizes the Attack
rxkov profile
Rxkov

MCP Tool Schema Poisoning: When the Framework Layer Authorizes the Attack

#cybersecurity #llm #mcp #security
Comments
6 min read
Prompt Caching Is a Timing Oracle: How the 41-80% Cost Win Becomes Cross-Tenant System Prompt Extraction
rxkov profile
Rxkov

Prompt Caching Is a Timing Oracle: How the 41-80% Cost Win Becomes Cross-Tenant System Prompt Extraction

#api #cybersecurity #llm #security
Comments
4 min read
One API Key Across OpenAI, Claude and Gemini: Chatbot Fallback Options for SaaS Apps
colemitchell4991 profile

One API Key Across OpenAI, Claude and Gemini: Chatbot Fallback Options for SaaS Apps

#chatbot #llm #api #saas
Comments
7 min read
Your agent's memory is a liability: track state, not history
pierrelaurentmedori profile

Your agent's memory is a liability: track state, not history

#ai #llm #architecture #performance
10
Picked as gem Comments 6
10 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.