DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The Agentic Loop Explained: Step Through the Plan, Build, Judge and Repeat Loop Behind AI Coding Agents

The Agentic Loop Explained: Step Through the Plan, Build, Judge and Repeat Loop Behind AI Coding Agents

13
Comments 2
6 min read
LLMs are compressors. So I chatted with gzip

LLMs are compressors. So I chatted with gzip

12
Comments
12 min read
Your MCP Servers Eat 24,000 Tokens Before You Type

Your MCP Servers Eat 24,000 Tokens Before You Type

Comments 1
6 min read
I let an LLM fill my AI tools directory. 11 months later, 41% of its picks were dead.

I let an LLM fill my AI tools directory. 11 months later, 41% of its picks were dead.

Comments
6 min read
The Rigor Ratchet: adversarial field notes from testing a frontier preview model on myself

The Rigor Ratchet: adversarial field notes from testing a frontier preview model on myself

1
Comments 2
5 min read
Speculative Decoding Acceptance Rate: Why 70% Caps You Near 2x

Speculative Decoding Acceptance Rate: Why 70% Caps You Near 2x

Comments 1
7 min read
How to get up to 2.3 faster GLM and DeepSeek inference by switching providers

How to get up to 2.3 faster GLM and DeepSeek inference by switching providers

Comments
4 min read
One Question to a RAG Chatbot Leaked Another Customer's Secret Price

One Question to a RAG Chatbot Leaked Another Customer's Secret Price

Comments
2 min read
Um modelo de 1.7B consegue igualar um LLM 4,7x maior? Destilando o Qwen3-8B com QLoRA em avaliações reais em PT-BR

Um modelo de 1.7B consegue igualar um LLM 4,7x maior? Destilando o Qwen3-8B com QLoRA em avaliações reais em PT-BR

1
Comments
9 min read
How I run an AI software factory

How I run an AI software factory

Comments
2 min read
Using AI for Anonymity

Using AI for Anonymity

9
Picked as gem Comments
6 min read
Prompt injection is a permissions problem

Prompt injection is a permissions problem

Comments
7 min read
Qwen4-Max: Alibaba's Biggest Model Yet Is Cheap, and Closed

Qwen4-Max: Alibaba's Biggest Model Yet Is Cheap, and Closed

Comments 1
3 min read
How to Tell Whether the Model Behind Your API Got Worse

How to Tell Whether the Model Behind Your API Got Worse

Comments 1
3 min read
What I Cut First When Reviewing a Multi-Subagent AI Architecture

What I Cut First When Reviewing a Multi-Subagent AI Architecture

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