DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
AI Coding Agents Need Runtime Guardrails, Not Just Human Review

AI Coding Agents Need Runtime Guardrails, Not Just Human Review

Comments
3 min read
'World Models' Will Be the Next Buzzword. The Man Saying That Just Raised $1B to Build One

Explores LeCun's architectural bet

'World Models' Will Be the Next Buzzword. The Man Saying That Just Raised $1B to Build One

15
Comments 5
8 min read
Securing RAG: Why the Retrieval Pipeline Is Your New Attack Surface

Securing RAG: Why the Retrieval Pipeline Is Your New Attack Surface

1
Comments
4 min read
A11: Stable Reasoning Under Moral Paradox — A Full Vertical Pass Through “What Is Good and Evil?”

A11: Stable Reasoning Under Moral Paradox — A Full Vertical Pass Through “What Is Good and Evil?”

Comments
4 min read
I Fabricated a Claim About LLM Judges. Then I Ran the Apology Experiment.

Rigorous self-correction via 600 test calls

I Fabricated a Claim About LLM Judges. Then I Ran the Apology Experiment.

1
Comments 5
8 min read
How I Shrunk My Agent's Core from 15 to 9: Why Hit Rate Alone Can't Tell You Which Rules to Retire

How I Shrunk My Agent's Core from 15 to 9: Why Hit Rate Alone Can't Tell You Which Rules to Retire

1
Comments
10 min read
Do not treat LangGraph as a longer chain: define state, interrupts, and recovery first

Do not treat LangGraph as a longer chain: define state, interrupts, and recovery first

Comments
4 min read
From Code to Governance: The Complete Guide to LLM Token Optimization

From Code to Governance: The Complete Guide to LLM Token Optimization

2
Comments
8 min read
Sizing a Mac mini M4 for Local AI: An Architect's Breakdown by Task

Sizing a Mac mini M4 for Local AI: An Architect's Breakdown by Task

1
Comments 2
4 min read
I Planned 10 LLM Evaluation Experiments And Only Ran 1. It Was Enough.

I Planned 10 LLM Evaluation Experiments And Only Ran 1. It Was Enough.

5
Comments 2
13 min read
Computer-Use Agents Hit 66% on OSWorld. The Other 34% Is a Data Problem.

Computer-Use Agents Hit 66% on OSWorld. The Other 34% Is a Data Problem.

Comments
6 min read
How to Use DeepSeek and Qwen API Outside China

How to Use DeepSeek and Qwen API Outside China

Comments
2 min read
The 5 Things Your LLM Benchmark Misses That Actually Decide the Winner

The 5 Things Your LLM Benchmark Misses That Actually Decide the Winner

Comments
7 min read
Model Weights

Model Weights

1
Comments
3 min read
The Open-Model Cost Chart Everyone's Sharing Is API Prices. Here's What Self-Hosting Actually Gets You (Measured)

The Open-Model Cost Chart Everyone's Sharing Is API Prices. Here's What Self-Hosting Actually Gets You (Measured)

1
Comments
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.