DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
HADS — A Simple Convention for Writing Docs That AI Can Actually Read

HADS — A Simple Convention for Writing Docs That AI Can Actually Read

Comments 1
3 min read
I Benchmarked 7 LLMs on Cross-Domain MCP Orchestration. All 7 Found the Same Gap.

I Benchmarked 7 LLMs on Cross-Domain MCP Orchestration. All 7 Found the Same Gap.

1
Comments 2
3 min read
NVIDIA AI Releases Nemotron-Terminal: A Systematic Data Engineering Pipeline for Scaling LLM Terminal Agents

NVIDIA AI Releases Nemotron-Terminal: A Systematic Data Engineering Pipeline for Scaling LLM Terminal Agents

Comments
4 min read
Data Agents Finally Get Real: DAComp & DP-Bench Crush the "erfect Query" Myth

Data Agents Finally Get Real: DAComp & DP-Bench Crush the "erfect Query" Myth

Comments 1
3 min read
NVIDIA AI Releases Nemotron-Terminal: A Systematic Data Engineering Pipeline for Scaling LLM Terminal Agents

NVIDIA AI Releases Nemotron-Terminal: A Systematic Data Engineering Pipeline for Scaling LLM Terminal Agents

Comments
4 min read
Acelerando o Design de Arquitetura com IA: Lições de 100 Milhões de Tokens e 11 Sessões

Acelerando o Design de Arquitetura com IA: Lições de 100 Milhões de Tokens e 11 Sessões

1
Comments
8 min read
I Built Stacks Skills — Because AI Agents Are Confidently Wrong About Stacks

I Built Stacks Skills — Because AI Agents Are Confidently Wrong About Stacks

1
Comments
4 min read
16-bit AI Quality at 11-bit Size? How DFloat11 achieves Lossless LLM Compression

16-bit AI Quality at 11-bit Size? How DFloat11 achieves Lossless LLM Compression

1
Comments
2 min read
Give Your Local LLM a Memory That Actually Works

Give Your Local LLM a Memory That Actually Works

2
Comments
2 min read
How to Set Up OpenClaw & Ollama for a Private AI Assistant

How to Set Up OpenClaw & Ollama for a Private AI Assistant

1
Comments
3 min read
CAG v1.5: Mode-Aware Control and Anchor Lifecycle Management

CAG v1.5: Mode-Aware Control and Anchor Lifecycle Management

Comments
2 min read
Agentic Coding: Rules, skills, subagents, and reflection—how we steer models so multi-step work stays coherent.

Agentic Coding: Rules, skills, subagents, and reflection—how we steer models so multi-step work stays coherent.

8
Comments 2
4 min read
Your AI generated code is "almost right", and that is actually WORSE than it being "wrong".

Your AI generated code is "almost right", and that is actually WORSE than it being "wrong".

Comments
2 min read
OpenClaw Custom Model Configuration: Connect Any AI Model You Want

OpenClaw Custom Model Configuration: Connect Any AI Model You Want

Comments
4 min read
I benchmarked 24 local LLM models for OpenClaw agent tool calling on RTX 3090

I benchmarked 24 local LLM models for OpenClaw agent tool calling on RTX 3090

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