DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Evals: How You Know the Agent Works in Production
rxkov profile
Rxkov

Evals: How You Know the Agent Works in Production

#agentic #llm #evals #testing
Comments 1
3 min read
handoff: Give the Next AI Agent the Context It Actually Needs
shubham399 profile

handoff: Give the Next AI Agent the Context It Actually Needs

#ai #llm #promptengineering #productivity
2
Comments
5 min read
GRPO, Dr. GRPO, and DAPO Explained — The One Identity That Unifies All Three
cofldus profile

GRPO, Dr. GRPO, and DAPO Explained — The One Identity That Unifies All Three

#machinelearning #python #deeplearning #llm
Comments
5 min read
AI Agent Long-Term Memory Is an Unguarded Database: How Poisoning Attacks Survive Across Sessions
rxkov profile
Rxkov

AI Agent Long-Term Memory Is an Unguarded Database: How Poisoning Attacks Survive Across Sessions

#ai #cybersecurity #llm #security
Comments
5 min read
Specification Gaming Is an Attack Surface, Not an Alignment Footnote
rxkov profile
Rxkov

Specification Gaming Is an Attack Surface, Not an Alignment Footnote

#agents #ai #llm #security
Comments
5 min read
AI Voice Agent with Function Calling — Calling Real APIs Mid-Conversation in Python
harpreetseehra profile

AI Voice Agent with Function Calling — Calling Real APIs Mid-Conversation in Python

#agents #ai #llm #python
Comments
8 min read
System Prompt Confidentiality Is Security by Obscurity
rxkov profile
Rxkov

System Prompt Confidentiality Is Security by Obscurity

#ai #cybersecurity #llm #security
Comments
4 min read
Indirect Prompt Injection via API Responses: The Attack Agents Cannot Stop at the LLM Layer
rxkov profile
Rxkov

Indirect Prompt Injection via API Responses: The Attack Agents Cannot Stop at the LLM Layer

#agents #cybersecurity #llm #security
Comments
5 min read
Agent Cost Optimization: Token Accounting, Cache, and Dynamic Dispatching
rxkov profile
Rxkov

Agent Cost Optimization: Token Accounting, Cache, and Dynamic Dispatching

#agentic #llm #cost #optimization
Comments
4 min read
The Sandbox That Exists Only in the System Prompt
rxkov profile
Rxkov

The Sandbox That Exists Only in the System Prompt

#agents #cybersecurity #llm #security
Comments
5 min read
99.4% Accurate but still completely useless?
rajinh24 profile

99.4% Accurate but still completely useless?

#machinelearning #llm #mlops #datascience
Comments 1
2 min read
Pricing and Portability: What Survives When the Numbers Change
rxkov profile
Rxkov

Pricing and Portability: What Survives When the Numbers Change

#agentic #llm #pricing #portability
Comments
3 min read
The Harness Is the Binding Constraint, Not the Model
rxkov profile
Rxkov

The Harness Is the Binding Constraint, Not the Model

#agents #ai #architecture #llm
Comments
6 min read
MCP Servers: When curl Becomes a Trap and Typed Tools Solve It
rxkov profile
Rxkov

MCP Servers: When curl Becomes a Trap and Typed Tools Solve It

#agentic #mcp #llm #tools
Comments
4 min read
Hooks: Intercepting Tool Calls Before the Damage Happens
rxkov profile
Rxkov

Hooks: Intercepting Tool Calls Before the Damage Happens

#agentic #llm #hooks #security
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.