DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Local LLM Acceleration & Large Open Model Management: Nemotron-Labs, Delta Weight Sync, PyTorch Profiling

Local LLM Acceleration & Large Open Model Management: Nemotron-Labs, Delta Weight Sync, PyTorch Profiling

Comments
4 min read
The AI Cost-Modeling Handbook: I let Claude do the modeling, but never the arithmetic

The AI Cost-Modeling Handbook: I let Claude do the modeling, but never the arithmetic

7
Comments
11 min read
Local LLM Advances: Holo3.1 Agents, Headroom Token Compression & Open-LLM-VTuber for Local Inference

Local LLM Advances: Holo3.1 Agents, Headroom Token Compression & Open-LLM-VTuber for Local Inference

1
Comments
3 min read
Building a Practical AI Assistant with Python: From Prompt to Production Thinking

Building a Practical AI Assistant with Python: From Prompt to Production Thinking

6
Comments 4
3 min read
Phase 1: Document Ingestion - The Hidden Complexity Before Embeddings

Phase 1: Document Ingestion - The Hidden Complexity Before Embeddings

3
Comments
20 min read
One Ruler to Measure Them All: How Language Affects LLM Quality

One Ruler to Measure Them All: How Language Affects LLM Quality

Comments
2 min read
Claude Opus 4.8 on Synthorai: Caching & TTL vs 4.7/4.6

Claude Opus 4.8 on Synthorai: Caching & TTL vs 4.7/4.6

Comments
7 min read
Contorium — A Project Cognitive Runtime for AI-Native Development

Contorium — A Project Cognitive Runtime for AI-Native Development

1
Comments 6
2 min read
How We Reduced LLM Latency by 89% and Token Usage by 91% in a Production Chrome Extension

How We Reduced LLM Latency by 89% and Token Usage by 91% in a Production Chrome Extension

1
Comments
2 min read
AI Conf 2026: Classic ML Is Dead, Everyone's Building Agents

AI Conf 2026: Classic ML Is Dead, Everyone's Building Agents

1
Comments
2 min read
One Ruler to Measure Them All: How Language Affects LLM Quality

One Ruler to Measure Them All: How Language Affects LLM Quality

1
Comments
2 min read
Claude Opus 4.8 Review: The Dynamic Workflow Tool Changes What's Possible for AI Agents

Claude Opus 4.8 Review: The Dynamic Workflow Tool Changes What's Possible for AI Agents

Comments
8 min read
Most AI-generated tests are written once and never questioned. That's the bug.

Most AI-generated tests are written once and never questioned. That's the bug.

Comments
3 min read
I review AI output for a living. Here's me getting it wrong — with the receipt.

I review AI output for a living. Here's me getting it wrong — with the receipt.

Comments
3 min read
The Fine-Tuning Trap: How Enterprises Are Accidentally Handing Their IP to AI Providers

The Fine-Tuning Trap: How Enterprises Are Accidentally Handing Their IP to AI Providers

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