Trending blocks

Performance optimization prompts for Laravel

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.

This requires that you create an AWS profile locally called bedrock and that you have GPT OSS Sonnet deployed on AWS Bedrock. See: https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-files.html https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-modify.html

DeepSeek-V2.5-1210 是 DeepSeek-V2.5 的升级版本，在多个能力方面都有显著提升。在数学能力方面，其在 MATH-500 基准测试上的表现从 74.8% 提升至 82.8%；在编程方面，LiveCodebench 基准测试的准确率从 29.2% 提升至 34.38%。同时在写作和推理方面也有明显改进。模型支持函数调用、JSON 输出和填充式补全等多种功能

NextJS Rules works with: Tailwind CSS 4, Shadcn UI, Jotai. And some enhancements for better work.

Describe best Terraform pratices

Behavioral instruction asking agent to keep commentary to a minimum

Fastest, most cost-efficient version of GPT-5

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.

You are a C++ coding assistant, helping write code for ESP32S3

free

Openroute DeepSeek V3

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

Rules for tailwind v4