正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Don't let AI write code blindly. In Antigravity, request an "Implementation Plan" artifact first. Review the architecture, edit the markdown logic, and then approve execution. Control the outcome, don't just hope for it.

Google Antigravity

167,464 subscribers

184,781 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

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

Holy moly Never seen someone being that bullish for AI developement as Dario Amodei: - There's just an exponential just like we had an exponential with Moore's law - I think the models are just going to get more and more capable at everything - I've had internal people at Anthropic say, "I don't write any code anymore. I don't write I don't open up an editor and write code. I just let Claude code write the first draft and and all I do is edit it. - What what we're going to see in the future is just like we've going to be seen in the past except more so - the models are just going to get more and more intellectually capable and you know the the revenue is going to keep adding zeros. holy moly, Dario!

Holy moly Never seen someone being that bullish for AI developement as Dario Amodei: - There's just an exponential just like we had an exponential with Moore's law - I think the models are just going to get more and more capable at everything - I've had internal people at Anthropic say, "I don't write any code anymore. I don't write I don't open up an editor and write code. I just let Claude code write the first draft and and all I do is edit it. - What what we're going to see in the future is just like we've going to be seen in the past except more so - the models are just going to get more and more intellectually capable and you know the the revenue is going to keep adding zeros. holy moly, Dario!

Chubby♨️

77,711 次观看 • 6 个月前

The best programmers don't write code anymore. They write a spec. A test. An eval. T Then they turn the AI on and walk away for hours. It runs. It ships. They review. Evals are the unlock most devs are sleeping on. Here's how top agent teams build them right.

The best programmers don't write code anymore. They write a spec. A test. An eval. T Then they turn the AI on and walk away for hours. It runs. It ships. They review. Evals are the unlock most devs are sleeping on. Here's how top agent teams build them right.

Rohit

690,326 次观看 • 2 个月前

New in Claude Code: /ultraplan Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal. Available now in preview for all users with CC on the web enabled.

New in Claude Code: /ultraplan Claude builds an implementation plan for you on the web. You can read it and edit it, then run the plan on the web or back in your terminal. Available now in preview for all users with CC on the web enabled.

Thariq

1,296,450 次观看 • 1 个月前

Start leading a team of parallel agents. Background tasks for your agents. High-level architecture for you. Don’t just write code, orchestrate it.

Start leading a team of parallel agents. Background tasks for your agents. High-level architecture for you. Don’t just write code, orchestrate it.

Google Antigravity

112,887 次观看 • 4 个月前

Feed your todos right into Cursor as markdown and it will write the code for you. The future is letting AI do the work for you while you guide it.

Feed your todos right into Cursor as markdown and it will write the code for you. The future is letting AI do the work for you while you guide it.

Mckay Wrigley

245,007 次观看 • 1 年前

I built 3 functional web apps in 4min… on my phone! Replit ⠕ Agent don’t just review and write code, their AI agents plan the functions, create development environment, install dependencies, write the code, configure databases and deploy. Is this the beginning of the end of paying for software? What’d you create?

I built 3 functional web apps in 4min… on my phone! Replit ⠕ Agent don’t just review and write code, their AI agents plan the functions, create development environment, install dependencies, write the code, configure databases and deploy. Is this the beginning of the end of paying for software? What’d you create?

Sander Saar

86,072 次观看 • 1 年前

Introducing CodeRabbit Plugin for Claude Code! The CodeRabbit plugin for Claude Code creates an autonomous AI development workflow, helping you write and fix code without manual intervention. Type /coderabbit:review (or just say “review my code”) to get AI-powered fixes directly in your dev flow! Try it today, it’s free!

Introducing CodeRabbit Plugin for Claude Code! The CodeRabbit plugin for Claude Code creates an autonomous AI development workflow, helping you write and fix code without manual intervention. Type /coderabbit:review (or just say “review my code”) to get AI-powered fixes directly in your dev flow! Try it today, it’s free!

CodeRabbit

27,190 次观看 • 4 个月前

A live look at Planning Mode in action with Andy Zhang on the Flutter show. 📄 Implementation Plan – the agent’s logic ✍️ Feedback – leaving comments on that plan 🧾 Walkthrough – proof of the agent’s work

A live look at Planning Mode in action with Andy Zhang on the Flutter show. 📄 Implementation Plan – the agent’s logic ✍️ Feedback – leaving comments on that plan 🧾 Walkthrough – proof of the agent’s work

Google Antigravity

91,684 次观看 • 6 个月前

Larry Ellison says AI is now writing Oracle's Code. "We just tell the model what we want the program to do, and then the AI comes up with a step-by-step process to actually do it. We don't write the procedure, we declare our intent"

Larry Ellison says AI is now writing Oracle's Code. "We just tell the model what we want the program to do, and then the AI comes up with a step-by-step process to actually do it. We don't write the procedure, we declare our intent"

Rohan Paul

67,399 次观看 • 19 天前

"Don't cry it's just an edit" The edit:

"Don't cry it's just an edit" The edit:

ruza

41,631 次观看 • 5 个月前

“Don't cry it's just an edit" The edit:

“Don't cry it's just an edit" The edit:

Rish⁷

13,714 次观看 • 1 个月前

Collaborate with an Asynchronous Agent. In Antigravity, don't wait for the output. Comment on the agent's artifacts in real-time to steer the ship without stopping the engine.

Collaborate with an Asynchronous Agent. In Antigravity, don't wait for the output. Comment on the agent's artifacts in real-time to steer the ship without stopping the engine.

Google Antigravity

88,797 次观看 • 3 个月前

Better feedback = Better code. Artifacts are the agent’s proof of work. Review plans, screen recordings, and code changes. Then, leave feedback to keep the agent on track. Try it today:

Better feedback = Better code. Artifacts are the agent’s proof of work. Review plans, screen recordings, and code changes. Then, leave feedback to keep the agent on track. Try it today:

Google Antigravity

82,293 次观看 • 6 个月前

CODE EXECUTION IN CANVAS🎨 Canvas becomes an automated SWE and a data scientist. Search for API docs, ask the model to write code and execute, get the plot!

CODE EXECUTION IN CANVAS🎨 Canvas becomes an automated SWE and a data scientist. Search for API docs, ask the model to write code and execute, get the plot!

Karina Nguyen

46,579 次观看 • 1 年前

This is pretty neat. You can write code with Cline, review it with CodeRabbit, and then handover the review context right back into Cline. (all in the same task)

This is pretty neat. You can write code with Cline, review it with CodeRabbit, and then handover the review context right back into Cline. (all in the same task)

Cline

23,011 次观看 • 11 个月前

LeetCode is dead. Developers don't write code line-by-line anymore. They orchestrate AI agents working in parallel, review AI-generated code, and make architectural decisions. That's the job now. But most interview processes haven't caught up. They still test algorithm memorization instead of AI fluency, code review, and judgment. We're building assessments for next-gen hiring that mirror how developers actually work. Here's how we think about it:

LeetCode is dead. Developers don't write code line-by-line anymore. They orchestrate AI agents working in parallel, review AI-generated code, and make architectural decisions. That's the job now. But most interview processes haven't caught up. They still test algorithm memorization instead of AI fluency, code review, and judgment. We're building assessments for next-gen hiring that mirror how developers actually work. Here's how we think about it:

HackerRank

342,700 次观看 • 1 个月前

Just added a GitHub review station to the OpenClaw 3D office. Sound on 🔊 You can now: • Approve PRs • Comment on changes • Request updates All without leaving the office. Code review just became… spatial.

Just added a GitHub review station to the OpenClaw 3D office. Sound on 🔊 You can now: • Approve PRs • Comment on changes • Request updates All without leaving the office. Code review just became… spatial.

Luke The Dev

13,371 次观看 • 2 个月前

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Google Antigravity

89,362 次观看 • 4 个月前

I'm going to let you in on a little secret: the Trump Administration is using classified briefings as an excuse to hide the truth from you. They don't have a plan for this war. They don't have a plan to lower your costs. They just don't want to admit it publicly.

I'm going to let you in on a little secret: the Trump Administration is using classified briefings as an excuse to hide the truth from you. They don't have a plan for this war. They don't have a plan to lower your costs. They just don't want to admit it publicly.

Senator Andy Kim

22,580 次观看 • 2 个月前