close

DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Working Set That Never Saturated

The Working Set That Never Saturated

Comments 1
6 min read
Amazon Nova 2: A Developer's Guide to Lite, Pro, and Omni

Amazon Nova 2: A Developer's Guide to Lite, Pro, and Omni

Comments 1
7 min read
What Does a 1 Million Token Context Window Actually Look Like?

What Does a 1 Million Token Context Window Actually Look Like?

Comments 1
4 min read
Language is a routing problem, not a translation problem

Language is a routing problem, not a translation problem

BERJAYA BERJAYA BERJAYA 6
Comments 2
3 min read
Stop stuffing the web into 7B weights

Stop stuffing the web into 7B weights

BERJAYA BERJAYA 5
Comments
3 min read
Swapping every model in a RAG

Swapping every model in a RAG

BERJAYA 1
Comments 2
9 min read
AI CURMUDGEON: AI is a backhoe

AI CURMUDGEON: AI is a backhoe

Comments
3 min read
Battle-Tested Multi-Agent Orchestration Patterns with Google ADK: Parallel, Sequential, and Persistent Sessions

Battle-Tested Multi-Agent Orchestration Patterns with Google ADK: Parallel, Sequential, and Persistent Sessions

Comments 1
4 min read
Claude 3.5 Sonnet is more than an upgrade. It’s a new workflow.

Claude 3.5 Sonnet is more than an upgrade. It’s a new workflow.

Comments
3 min read
Why I chose Gemma4b over Mistral 7b?

Why I chose Gemma4b over Mistral 7b?

Comments
4 min read
What Happens When an AI Agent Gets Stuck in a Loop?

What Happens When an AI Agent Gets Stuck in a Loop?

BERJAYA BERJAYA BERJAYA 5
Comments
7 min read
Claude Code plugin eval: gate skills on delta before you merge

Claude Code plugin eval: gate skills on delta before you merge

Comments 2
5 min read
DeepSeek V4.1 Flash API Cost: Matches V4 Pro at 3-6x Less per Answer

DeepSeek V4.1 Flash API Cost: Matches V4 Pro at 3-6x Less per Answer

Comments
12 min read
llama.cpp vs Ollama in 2026: Which Runtime Should You Run?

llama.cpp vs Ollama in 2026: Which Runtime Should You Run?

Comments
18 min read
Implementing AI Observability: Tracing LLM Calls End-to-End

Implementing AI Observability: Tracing LLM Calls End-to-End

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