DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
300+ languages doesn't mean what you think: three tiers of code understanding

300+ languages doesn't mean what you think: three tiers of code understanding

Comments
7 min read
Keeping the LLM out of the verdict

Keeping the LLM out of the verdict

Comments 1
5 min read
Understanding Tokens: How AI Models Process Text and Why It Matters for Cost, Context, and Agentic AI

Understanding Tokens: How AI Models Process Text and Why It Matters for Cost, Context, and Agentic AI

Comments
10 min read
I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path

I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path

Comments
2 min read
I created a tool to inspect full python codebases

I created a tool to inspect full python codebases

Comments
1 min read
"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"

"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"

Comments
7 min read
🤖 AI Context Engineering (Part 4): AI Agents - From Tool Calling to Multi-Step Workflows

🤖 AI Context Engineering (Part 4): AI Agents - From Tool Calling to Multi-Step Workflows

1
Comments
9 min read
I tested if system prompts actually matter, here's what I found

I tested if system prompts actually matter, here's what I found

Comments
2 min read
Claude Code Keeps Forgetting My Projects - Here's the Skill I Built to Make It Remember /project-registry

Claude Code Keeps Forgetting My Projects - Here's the Skill I Built to Make It Remember /project-registry

Comments
3 min read
Integrating AgentRouter with Tauric Research TradingAgents

Integrating AgentRouter with Tauric Research TradingAgents

Comments
4 min read
Your multi-agent system isn't hitting prompt cache. Your system prompt is the reason.

Your multi-agent system isn't hitting prompt cache. Your system prompt is the reason.

3
Comments 4
4 min read
One Prompt Template, Three Engines That Disagree

One Prompt Template, Three Engines That Disagree

Comments
6 min read
1. Self-Hosted AI: the LLM concepts you need to run models effectively

1. Self-Hosted AI: the LLM concepts you need to run models effectively

Comments
9 min read
Designing an End-to-End RAG Architecture from Scratch

Designing an End-to-End RAG Architecture from Scratch

11
Comments 2
8 min read
DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.

DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.

1
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.