DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Let 12 AI Models Predict the World Cup. The First 169 Picks Already Show a Pattern.

I Let 12 AI Models Predict the World Cup. The First 169 Picks Already Show a Pattern.

5
Comments
6 min read
Wire your AI agent into Macrokit's MCP server — and find out which workflows you should have encoded

Wire your AI agent into Macrokit's MCP server — and find out which workflows you should have encoded

1
Comments
3 min read
Your Agent Telemetry Ranks Your Routing Policy, Not Your Models

Your Agent Telemetry Ranks Your Routing Policy, Not Your Models

1
Comments 4
6 min read
I lint-scanned 36 popular MCP servers. A third of them are failing your agent.

I lint-scanned 36 popular MCP servers. A third of them are failing your agent.

11
Comments 28
5 min read
Gym Badges of Agentic Engineering (Part 1): Measuring Agent Success

Gym Badges of Agentic Engineering (Part 1): Measuring Agent Success

Comments
3 min read
What to restore when LiteLLM holds team keys, budgets and spend data

What to restore when LiteLLM holds team keys, budgets and spend data

2
Comments
8 min read
Run Qwen3.6-27B Locally: The Most Capable Open Model for a Single GPU

Run Qwen3.6-27B Locally: The Most Capable Open Model for a Single GPU

Comments
2 min read
TensorSharp: .NET Native Open Source Local LLM Inference Engine

TensorSharp: .NET Native Open Source Local LLM Inference Engine

Comments
1 min read
Six experiments on adversarial verification — and the 75% wall that didn't move

Six experiments on adversarial verification — and the 75% wall that didn't move

12
Comments 44
6 min read
Model Showdown Round 7: Five Local Models vs. One Cloud Model on a Real Coding Task

Model Showdown Round 7: Five Local Models vs. One Cloud Model on a Real Coding Task

1
Comments
9 min read
Step 3.7 Flash is a drop-in — except for one endpoint detail

Step 3.7 Flash is a drop-in — except for one endpoint detail

1
Comments
9 min read
Nemotron 3 Ultra went live June 4. Here's the call that works.

Nemotron 3 Ultra went live June 4. Here's the call that works.

Comments
7 min read
llama-bench skipped FA on capable GPUs — b9437 corrects it

llama-bench skipped FA on capable GPUs — b9437 corrects it

Comments
7 min read
I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

Comments
3 min read
Lately, I’ve been thinking about setting up my homelab again. I still…

Lately, I’ve been thinking about setting up my homelab again. I still…

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