DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
(The Voice) Multilingual Layer

(The Voice) Multilingual Layer

1
Comments
4 min read
Giving AI agents knowledge they were never trained on

Giving AI agents knowledge they were never trained on

4
Comments 5
4 min read
Test Your LLM Outputs in pytest (15ms, No API Key)

Test Your LLM Outputs in pytest (15ms, No API Key)

Comments
4 min read
AI한테 기억을 가르치려면, 잊는 법부터 가르쳐야 한다

AI한테 기억을 가르치려면, 잊는 법부터 가르쳐야 한다

Comments
2 min read
Llama4 108B Local Inference, MiniMax M2.7 GGUF Alert, & Ollama Security Scanner

Llama4 108B Local Inference, MiniMax M2.7 GGUF Alert, & Ollama Security Scanner

2
Comments
3 min read
Why your AI response restarts on page refresh (and what it takes to prevent it)

Why your AI response restarts on page refresh (and what it takes to prevent it)

Comments
3 min read
Persistent Identity Agents: Why Memory Isn’t Enough

Persistent Identity Agents: Why Memory Isn’t Enough

1
Comments
2 min read
Resume tokens and last-event IDs for LLM streaming: How they work & what they cost to build

Resume tokens and last-event IDs for LLM streaming: How they work & what they cost to build

Comments
6 min read
Building a Voice-Controlled AI Agent That Runs Entirely on Your Laptop

Building a Voice-Controlled AI Agent That Runs Entirely on Your Laptop

Comments
3 min read
Challenges and Accomplishments in the task of building an AI based intent classifier

Challenges and Accomplishments in the task of building an AI based intent classifier

Comments
2 min read
Build LLM Guardrails in 3 Lines of Python (No API Key, No Cloud)

Build LLM Guardrails in 3 Lines of Python (No API Key, No Cloud)

Comments
6 min read
Open Source LLMs in 2026: Can Llama 4 / DeepSeek V3 Replace GPT for Business?

Open Source LLMs in 2026: Can Llama 4 / DeepSeek V3 Replace GPT for Business?

Comments
7 min read
Show HN: Needle distilled Gemini tool calling into 26M parameters — technical read, zero hype

Show HN: Needle distilled Gemini tool calling into 26M parameters — technical read, zero hype

Comments
8 min read
From Voice to Code: Architecting a Local AI Agent with Llama 3.2 & Streamlit

From Voice to Code: Architecting a Local AI Agent with Llama 3.2 & Streamlit

Comments
2 min read
Four LLM Workflows That Actually Survive Production

Four LLM Workflows That Actually Survive Production

5
Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.