DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Prompt Stuffing Is Killing Your Agent

Prompt Stuffing Is Killing Your Agent

32
Comments 2
6 min read
Why the f*** does AI always use em dashes — the involuntary AI watermark

Why the f*** does AI always use em dashes — the involuntary AI watermark

4
Comments 8
2 min read
TurboQuant MoE 0.3.0

TurboQuant MoE 0.3.0

Comments
1 min read
Part 1 of 3 — Engineering Intent Series - Stop Prompting, Start Compiling: The Path to Predictable AI-Generated Code

Part 1 of 3 — Engineering Intent Series - Stop Prompting, Start Compiling: The Path to Predictable AI-Generated Code

Comments
3 min read
Part 2 of 3 — Engineering Intent Series - Engineering Intent: The Anatomy of ISL

Part 2 of 3 — Engineering Intent Series - Engineering Intent: The Anatomy of ISL

Comments
4 min read
TERSE — A New Serialization Format Built for LLMs

TERSE — A New Serialization Format Built for LLMs

Comments
4 min read
Part 3 of 3 — Engineering Intent Series -- Inside the Machine: The ISL Build Pipeline

Part 3 of 3 — Engineering Intent Series -- Inside the Machine: The ISL Build Pipeline

Comments
5 min read
Claude Code's Compaction Engine: What the Source Code Actually Reveals

Claude Code's Compaction Engine: What the Source Code Actually Reveals

Comments
2 min read
What Karpathy's Autoresearch Unlocked for Me

What Karpathy's Autoresearch Unlocked for Me

Comments
2 min read
How TurboQuant Works for LLMs and Why It Uses Much Less RAM

How TurboQuant Works for LLMs and Why It Uses Much Less RAM

Comments
5 min read
Three Things Had to Align: The Real Story Behind the LLM Revolution

Three Things Had to Align: The Real Story Behind the LLM Revolution

Comments
8 min read
Build an End-to-End RAG Pipeline for LLM Applications

Build an End-to-End RAG Pipeline for LLM Applications

Comments
12 min read
I Tested 6 Attacks on Multi-Agent Systems — Here's Which Ones Agents Can't See

I Tested 6 Attacks on Multi-Agent Systems — Here's Which Ones Agents Can't See

Comments
4 min read
MoE Beat Dense 27B by 2.4x on 8GB VRAM — The 35B-A3B Benchmark Nobody Expected

MoE Beat Dense 27B by 2.4x on 8GB VRAM — The 35B-A3B Benchmark Nobody Expected

Comments
5 min read
LLM Inference Optimization: Techniques That Actually Reduce Latency and Cost

LLM Inference Optimization: Techniques That Actually Reduce Latency and Cost

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