Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Deploy Pixtral at Scale: vLLM + Docker Made Simple

Deploy Pixtral at Scale: vLLM + Docker Made Simple

45
Comments
2 min read
Building a smart, agentic email assistant
Cover image for Building a smart, agentic email assistant

Building a smart, agentic email assistant

1
Comments
9 min read
How to make AI code edits more accurate
Cover image for How to make AI code edits more accurate

How to make AI code edits more accurate

5
Comments 4
5 min read
OpenAI GPT-5 vs. Claude Opus 4.1: A coding comparison
Cover image for OpenAI GPT-5 vs. Claude Opus 4.1: A coding comparison

OpenAI GPT-5 vs. Claude Opus 4.1: A coding comparison

29
Comments 7
5 min read
Making New Languages Click with LLMs
Cover image for Making New Languages Click with LLMs

Making New Languages Click with LLMs

1
Comments 1
4 min read
Don’t Stop at RAG. AGENTIC RAG Actually Gets Things Done
Cover image for Don’t Stop at RAG. AGENTIC RAG Actually Gets Things Done

Don’t Stop at RAG. AGENTIC RAG Actually Gets Things Done

5
Comments
2 min read
How I use LLMs: BadVibez Coding
Cover image for How I use LLMs: BadVibez Coding

How I use LLMs: BadVibez Coding

Comments
5 min read
Building an AI-Powered Chest X-ray Analyzer with MedGemma 27B and Gradio
Cover image for Building an AI-Powered Chest X-ray Analyzer with MedGemma 27B and Gradio

Building an AI-Powered Chest X-ray Analyzer with MedGemma 27B and Gradio

6
Comments
16 min read
Kimi K2: The 1 Trillion Parameter Open-Source AI That's Redefining Agentic Intelligence
Cover image for Kimi K2: The 1 Trillion Parameter Open-Source AI That's Redefining Agentic Intelligence

Kimi K2: The 1 Trillion Parameter Open-Source AI That's Redefining Agentic Intelligence

Comments
5 min read
2025 Complete Guide: Qwen3-235B-A22B-Thinking-2507 - The New Benchmark for Open-Source Thinking Models
Cover image for 2025 Complete Guide: Qwen3-235B-A22B-Thinking-2507 - The New Benchmark for Open-Source Thinking Models

2025 Complete Guide: Qwen3-235B-A22B-Thinking-2507 - The New Benchmark for Open-Source Thinking Models

2
Comments
7 min read
The GPT-5 Paradox: Genius in Thought, Gaps in Safety
Cover image for The GPT-5 Paradox: Genius in Thought, Gaps in Safety

The GPT-5 Paradox: Genius in Thought, Gaps in Safety

6
Comments
17 min read
(Attempting to) Engineer the chaos out of AI agents
Cover image for (Attempting to) Engineer the chaos out of AI agents

(Attempting to) Engineer the chaos out of AI agents

1
Comments
7 min read
How to Trace RAG Applications Effortlessly

How to Trace RAG Applications Effortlessly

2
Comments
4 min read
The Best Platforms for Evaluating AI Models in 2025

The Best Platforms for Evaluating AI Models in 2025

2
Comments
5 min read
From Code to Cloud: A Three-Act Playbook for Enterprise AI Transformation
Cover image for From Code to Cloud: A Three-Act Playbook for Enterprise AI Transformation

From Code to Cloud: A Three-Act Playbook for Enterprise AI Transformation

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