DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
MCP doesn't replace function calling. Your MCP client still emits one.

MCP doesn't replace function calling. Your MCP client still emits one.

Comments 2
3 min read
25 LLM architecture blocks, side by side, in runnable PyTorch

25 LLM architecture blocks, side by side, in runnable PyTorch

Comments
8 min read
Does Jev remember 2023? A naive test says yes at p = 0.001. A within-company test says no.

Does Jev remember 2023? A naive test says yes at p = 0.001. A within-company test says no.

2
Comments
6 min read
Grok 4.6 da xAI: O Supercluster Colossus, Raciocínio Extremo, Arquitetura Multimodal e Implementação em Python

Grok 4.6 da xAI: O Supercluster Colossus, Raciocínio Extremo, Arquitetura Multimodal e Implementação em Python

Comments
16 min read
GLM-5.3 da Zhipu AI (Z.ai): O Supermodelo Aberto de 744B Parâmetros, Atenção Híbrida KDA e Implementação em Python

GLM-5.3 da Zhipu AI (Z.ai): O Supermodelo Aberto de 744B Parâmetros, Atenção Híbrida KDA e Implementação em Python

Comments
12 min read
DeepSeek 4.1: MoE de 1,2 TrilhĂŁo com MLA v2 e DualPipe

DeepSeek 4.1: MoE de 1,2 TrilhĂŁo com MLA v2 e DualPipe

Comments
12 min read
Claude Mythos 5.1: RaciocĂ­nio CientĂ­fico Formal da Anthropic

Claude Mythos 5.1: RaciocĂ­nio CientĂ­fico Formal da Anthropic

Comments
14 min read
In 2018 I hand-wrote a C++ deep learning framework so I'd never pad a batch. In 2023 LLM serving landed on the same structure.

In 2018 I hand-wrote a C++ deep learning framework so I'd never pad a batch. In 2023 LLM serving landed on the same structure.

Comments
13 min read
A Supersemana da IA: Claude Opus 5.5, GPT-6 e Grok

A Supersemana da IA: Claude Opus 5.5, GPT-6 e Grok

Comments
13 min read
Agentes de Voz em Tempo Real: WebRTC Full-Duplex com Gemini

Agentes de Voz em Tempo Real: WebRTC Full-Duplex com Gemini

Comments
10 min read
SGLang 2.0 e RadixAttention v2: InferĂŞncia de Alta Performance em 2026

SGLang 2.0 e RadixAttention v2: InferĂŞncia de Alta Performance em 2026

Comments
13 min read
Claude Code Cloud Sessions: Agentes AutĂ´nomos no Terminal com MCP

Claude Code Cloud Sessions: Agentes AutĂ´nomos no Terminal com MCP

Comments
12 min read
FlashAttention-4 em Blackwell B200: Pipelining de Kernels e FP4 Tensor Cores

FlashAttention-4 em Blackwell B200: Pipelining de Kernels e FP4 Tensor Cores

Comments
10 min read
I didn't fix the bug: contributing to a 20k-star ML repo by measuring it

I didn't fix the bug: contributing to a 20k-star ML repo by measuring it

Comments
11 min read
No LLM is allowed near my compliance decisions, and CI enforces it

No LLM is allowed near my compliance decisions, and CI enforces it

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