DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Claude Fable 5 on Databricks is a step-change for agentic workflows

Claude Fable 5 on Databricks is a step-change for agentic workflows

Comments
3 min read
Stop Using 'Skills' for Brainstorming. Build a Hook Instead. 🛠️

Stop Using 'Skills' for Brainstorming. Build a Hook Instead. 🛠️

1
Comments 1
3 min read
Claude Fable 5: Anthropic's First Mythos-Class Model for General Use

Claude Fable 5: Anthropic's First Mythos-Class Model for General Use

Comments
3 min read
Claude Fable 5: o primeiro modelo Mythos-class para uso geral

Claude Fable 5: o primeiro modelo Mythos-class para uso geral

Comments
4 min read
Flash Attention: what it does and why it matters

Flash Attention: what it does and why it matters

Comments
8 min read
Making a fleet of self-hosted LLM agents trustworthy

Making a fleet of self-hosted LLM agents trustworthy

1
Comments
6 min read
Ollama 0.30 GPU Boost: Faster local Qwen inference on NVIDIA

Ollama 0.30 GPU Boost: Faster local Qwen inference on NVIDIA

Comments
1 min read
Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

Comments
1 min read
Why We Added Rate Limits Between AI Agents

Why We Added Rate Limits Between AI Agents

Comments
3 min read
Your schema validation passes and the agent still picks the wrong tool. The bug is semantic.

Your schema validation passes and the agent still picks the wrong tool. The bug is semantic.

Comments
2 min read
The Prefill Wall: Why MTP's 2 Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)

The Prefill Wall: Why MTP's 2 Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)

Comments
4 min read
I Built an AI Agent That Writes Tests, Finds Bugs, and Opens PRs — Autonomously

I Built an AI Agent That Writes Tests, Finds Bugs, and Opens PRs — Autonomously

Comments 1
5 min read
I was fine-tuning a language model on a new language. The loss was perfect. It spoke Chinese.

I was fine-tuning a language model on a new language. The loss was perfect. It spoke Chinese.

Comments
3 min read
Model routing by task type: the savings math, the classifier overhead, and the A/B that proves it

Model routing by task type: the savings math, the classifier overhead, and the A/B that proves it

Comments
12 min read
My server pushes hints to agents — and the 3 iterations that led there

My server pushes hints to agents — and the 3 iterations that led there

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