Загрузка видео...

Не удалось загрузить видео

На главную

Hello, Cody. Cody answers code questions and writes code for you by reading your entire codebase and the code graph. Often magical, often frustratingly wrong...but getting better quickly. Rolling out to opt-in customers & Discord community members now.

156,401 просмотров • 3 лет назад •via X (Twitter)

Комментарии: 10

Фото профиля Newt Getrich
Newt Getrich3 лет назад

@DavidSacks Fantastic name!

Фото профиля Quinn Slack
Quinn Slack3 лет назад

@DavidSacks Same to you!

Фото профиля Vanna
Vanna3 лет назад

@DavidSacks Man, I just saw this paper and people are already doing this at the commercial level. 🤯

Фото профиля Quinn Slack
Quinn Slack3 лет назад

@DavidSacks Things move quickly. I love it!

Фото профиля Avadh Patel
Avadh Patel3 лет назад

Congratulations @sqs and your team on getting this out the door so fast! One feature request is to generate architecture diagrams from the connected code repos in Lucid charts!

Фото профиля Quinn Slack
Quinn Slack3 лет назад

Great idea. Here is Cody generating a graphviz diagram from a code file. Had to nudge it to not include dots in node IDs. Do you have an example of a perfect output diagram you want?

Фото профиля Jintao Zhang 张晋涛
Jintao Zhang 张晋涛3 лет назад

amazing feature

Фото профиля Alex Ewetumo
Alex Ewetumo3 лет назад

Is Cody built on OpenAI GPT-3/4 or did you guys train your own LLM ? If so, can you teach me how yall did that? I don't mind paying to learn it.

Фото профиля Quinn Slack
Quinn Slack3 лет назад

It's built with @AnthropicAI's Claude model. The differentiation is in the context-fetching; see

Фото профиля Kiril Videlov
Kiril Videlov3 лет назад

i'd love to try it out!

Похожие видео

Nothing beats Augment Code answering questions about large codebases. It's a free extension (works in VSCode, JetBrains, and NeoVim), and has a community edition you can run for free forever. Try this experiment: 1. Download any large open-source project from GitHub 2. Augment will index the code 3. Start asking questions about the codebase 4. Do the same using any other coding agent 5. Compare the speed and the depth of the answers you get If you have a small codebase, the differences with other coding agents won't be obvious, but if you are working on a large project, things will click immediately. Suggestion: download the Keras repository (~180,000 lines of code). I know the library well, and the answers I got from Augment were pretty impressive. By the way, Augment is a fully-fledged AI coding assistant. You can use its agent in every imaginable way: • To implement brand new functionality • To make quick edits to your code • To refactor existing functionality • To generate unit tests • To generate documentation • To handle GitHub—pull requests, commits, branching, etc My favorite feature is their "Next Edit" functionality: 1. You edit the code 2. Augment analyzes the change (across the entire codebase!) 3. Augment determines the ripple effects of that change 4. Augment suggests everything you need to update Here is a link to the tool: Thanks to the team at Augment Code for partnering with me on this post.

Santiago

34,977 просмотров • 1 год назад