DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Replaced JSON with TOON in My LLM Prompts and Saved 40% on Tokens.

I Replaced JSON with TOON in My LLM Prompts and Saved 40% on Tokens.

1
Comments
6 min read
Exploratory Installation of Unsloth on NVIDIA Jetson AGX Orin 64 GB

Exploratory Installation of Unsloth on NVIDIA Jetson AGX Orin 64 GB

Comments
8 min read
How I fixed LLM structured output failures in a PowerPoint translator (0 errors on 1,214 translations)

How I fixed LLM structured output failures in a PowerPoint translator (0 errors on 1,214 translations)

Comments 1
3 min read
🤖 SWE-agent — Deep Dive & Build-Your-Own Guide 📘

🤖 SWE-agent — Deep Dive & Build-Your-Own Guide 📘

6
Comments
31 min read
MCP Servers Are APIs — Monitor Them Like APIs

MCP Servers Are APIs — Monitor Them Like APIs

Comments
4 min read
Bluesky đẩy mạnh AI với Attie: công cụ tạo feed tuỳ biến trên AT Protocol (atproto)

Bluesky đẩy mạnh AI với Attie: công cụ tạo feed tuỳ biến trên AT Protocol (atproto)

Comments
7 min read
Why Your Agent Can Use a Database but Cant Delete a File

Why Your Agent Can Use a Database but Cant Delete a File

Comments
3 min read
The Flat Subscription Problem: Why Agents Break AI Pricing

The Flat Subscription Problem: Why Agents Break AI Pricing

Comments
4 min read
Code Mode for MCP: The Long-Tail Escape Hatch, Not the Front Door

Code Mode for MCP: The Long-Tail Escape Hatch, Not the Front Door

Comments 2
25 min read
Indexatron Update: Context-Aware Analysis with Local Vision Models

Indexatron Update: Context-Aware Analysis with Local Vision Models

1
Comments
5 min read
Performance Benchmarks of Bheeshma Diagnosis: How a megallm-Powered AI Medical Assistant Handles 20,000+ Records at Scale

Performance Benchmarks of Bheeshma Diagnosis: How a megallm-Powered AI Medical Assistant Handles 20,000+ Records at Scale

1
Comments
3 min read
The AI Stack: A Practical Guide to Building Your Own Intelligent Applications

The AI Stack: A Practical Guide to Building Your Own Intelligent Applications

Comments
5 min read
How I Built a Production-Ready RAG Pipeline in Python Without Going Crazy

How I Built a Production-Ready RAG Pipeline in Python Without Going Crazy

Comments
5 min read
I scored 14 popular AI frameworks on behavioral commitment — here's the data

I scored 14 popular AI frameworks on behavioral commitment — here's the data

1
Comments
3 min read
Gemma 4 Local Inference: Ollama Benchmarks, llama.cpp KV Cache Fix, NPU Deployments

Gemma 4 Local Inference: Ollama Benchmarks, llama.cpp KV Cache Fix, NPU Deployments

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