正在加载视频...

视频加载失败

My vibe coding workflow has changed since I started using Cursor Plan + Opus 4.5 more extensively. Before: Break down tasks into micro-prompts with specific tasks Now: Write a longer feature scope > Plan mode: Ask for proposals > Review proposed plans > Build I'm able to build an...

78,322 次观看 • 4 个月前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Learn to build and deploy GenAI pipelines in "Orchestrating Workflows for GenAI Applications", built in partnership with Astronomer and taught by Kenten Danas, the company's DevRel Senior Manager, and Tamara Fingerlin, developer advocate. Many GenAI applications require executing a pipeline comprising many steps. For example, a RAG app for recommending books might ingest and embed book descriptions, store the embeddings in a vector database, and later use the database to retrieve and recommend specific books based on a user query. After having prototyped this -- maybe in a Jupyter notebook -- how do you turn this into a reliable, repeatable workflow to run in production? In this short course, you’ll learn to build reliable GenAI pipelines and orchestrate them using the popular open-source tool Airflow 3.0. You’ll learn to break down a workflow into discrete tasks so that an orchestration framework can schedule tasks to run in the right order at the right time (using time-based or data-aware triggers), and execute tasks in parallel when possible. It can also use retries to recover gracefully from failure (such as transient API rate limits) and provide observability (using Airflow UI) to help you track the status of the pipeline. You'll do this by using Airflow dags, which helps sequence tasks that need to run in a specific order, with clear task dependencies. By the end of this course, you’ll know how to turn your prototype Jupyter notebook or Python script into production-ready workflow. Please sign up here:

Andrew Ng

73,532 次观看 • 11 个月前

I've been spending more time with Bezi to see how far I can push vibe coding a game on the Unity Editor. So far, I'm pretty happy with what I can achieve with Bezi. Here are some learnings: - Even though I use Bezi to do all agentic coding, I still have to perform a few small manual tasks in the Unity Editor - As a result, I feel like I am getting a hang of Unity's complex and clunky UI, which actually feels good! - This is one of those examples where Vibe Coding is a great way to learn game dev. - For big features, I can't state the importance of asking the agent to create a plan first before implementing the feature. It can work wonders. Most of the bigger features/ssytems starts with a clear plan. - The biggest strength about working with Unity Engine is the Unity Asset Store, there's so much good stuff in there, 3D assets, shaders, vfx etc that can really spice up your game, that other game enginers will need to build from scratch. - Because Unity Assets Stores sell UI assets packs, I was able to implement decent looking UI fairly quickly. For those of you that vibe code games, you know how much of a pain it is to implement UI. - I did meet a few hiccups along the way where Bezi seems to struggle a little with implementing some features, but usually with some retries it works out at the end, though it burns a ton of tokens. After spending more time with Bezi, I'm still feeling good about using it. I am able to get this PvZ style autobattler working in a few days!

Danny Limanseta

13,319 次观看 • 2 个月前