DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How to Run Reliable Local LLM Agents on an RTX 3090: A Benchmark (5 Models, Priced in Watts)

How to Run Reliable Local LLM Agents on an RTX 3090: A Benchmark (5 Models, Priced in Watts)

1
Comments
3 min read
OpenAI ลดราคา 80%, สงครามราคา AI กำลังเปลี่ยนวิธีที่เราคิดเรื่องต้นทุน

OpenAI ลดราคา 80%, สงครามราคา AI กำลังเปลี่ยนวิธีที่เราคิดเรื่องต้นทุน

Comments
2 min read
I use AI agents to code. Four checks I built to trust them.

I use AI agents to code. Four checks I built to trust them.

2
Comments 3
5 min read
Getting Started with Ollama: Run LLMs Locally in 10 Minutes

Getting Started with Ollama: Run LLMs Locally in 10 Minutes

Comments
5 min read
What is a context window, actually?

Readers debate if large windows replace memory

What is a context window, actually?

29
Comments 22
4 min read
I Built a Plain-Text Format for Portable AI Companion Memory

I Built a Plain-Text Format for Portable AI Companion Memory

Comments
4 min read
How to build a CS2 live score Discord bot

How to build a CS2 live score Discord bot

Comments
3 min read
Where you host your MCP server decides whether it still works in three months

Where you host your MCP server decides whether it still works in three months

Comments 11
6 min read
The all-purpose agent isn't an architecture. It's a single point of failure with a system prompt.

The all-purpose agent isn't an architecture. It's a single point of failure with a system prompt.

21
Comments 9
3 min read
PAL: Giving AI Agents Hands in the Physical World

PAL: Giving AI Agents Hands in the Physical World

Comments
4 min read
Introducing Hearth v0.3.0: Scale Long-Tail LLMs to Zero on Private Kubernetes

Introducing Hearth v0.3.0: Scale Long-Tail LLMs to Zero on Private Kubernetes

2
Comments 3
5 min read
Building FailureDNA: an agent memory that knows when not to trust itself

Building FailureDNA: an agent memory that knows when not to trust itself

Comments
4 min read
Why Your Claude Code Orchestrator Silently Stops Dispatching Subagents

Why Your Claude Code Orchestrator Silently Stops Dispatching Subagents

1
Comments 2
4 min read
"Dispatch: one week left on the kill-criteria clock — the honest state of every metric"

"Dispatch: one week left on the kill-criteria clock — the honest state of every metric"

Comments
3 min read
Memory Leak & 8-Second Diagnostic Crush

Memory Leak & 8-Second Diagnostic Crush

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