DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Detecting Context-Sensitive Behavior in AI Models: A Deep Dive into StealthEval Implementation

Detecting Context-Sensitive Behavior in AI Models: A Deep Dive into StealthEval Implementation

1
Comments
25 min read
Clean Architecture for AI Agents with Convo-Lang

Clean Architecture for AI Agents with Convo-Lang

Comments
5 min read
AI Agent VS Chatbot

AI Agent VS Chatbot

Comments
3 min read
Part 2: The 5 Types of Memory Every AI Agent Needs (And Why LLMs Can Only Do 2)

Part 2: The 5 Types of Memory Every AI Agent Needs (And Why LLMs Can Only Do 2)

Comments
6 min read
I Built an API for LLM JSON Validation in Rust — Here’s What I Learned

I Built an API for LLM JSON Validation in Rust — Here’s What I Learned

Comments
5 min read
Building SupportX AI Assist: A Multi-Agent IT Support System

Building SupportX AI Assist: A Multi-Agent IT Support System

Comments
7 min read
We Tested Claude Opus 4.6 and Gemini 3 Pro Against 50 Attacks. Both Scored 95/100 — But Failed Differently.

We Tested Claude Opus 4.6 and Gemini 3 Pro Against 50 Attacks. Both Scored 95/100 — But Failed Differently.

Comments
3 min read
Augustus: Open Source LLM Prompt Injection Scanner

Augustus: Open Source LLM Prompt Injection Scanner

Comments
5 min read
How We Achieved 30% Conversion Lift by Moving from GPT-4 to LoRA Adapters

How We Achieved 30% Conversion Lift by Moving from GPT-4 to LoRA Adapters

Comments
11 min read
I Spent 48 Hours Red-Teaming the "Magic AI Assistant" Everyone's Hyping. Here's What I Found.

I Spent 48 Hours Red-Teaming the "Magic AI Assistant" Everyone's Hyping. Here's What I Found.

Comments
9 min read
I Built an AI Companion on Telegram That Actually Remembers You

I Built an AI Companion on Telegram That Actually Remembers You

2
Comments
3 min read
Stop Paying Twice for AI — Turn Your CLI Agents Into Rubber Ducks

Stop Paying Twice for AI — Turn Your CLI Agents Into Rubber Ducks

1
Comments
6 min read
I built a “deterministic” LLM text rephraser with a validation pipeline - looking for architectural feedback

I built a “deterministic” LLM text rephraser with a validation pipeline - looking for architectural feedback

Comments
3 min read
Why I Replaced LangChain with 15KB of httpx

Why I Replaced LangChain with 15KB of httpx

Comments
6 min read
How to Design LLM Applications for Production: A System Design Guide

How to Design LLM Applications for Production: A System Design Guide

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