Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

The software factory is already here. We're seeing bots write code, bots review it, and humans reduced to dispatching the next tool in the chain. Using 500k+ PRs from Code Review Bench, we looked at one question: can the human leave the loop yet?

withmartian's profile picture

Martian

2,599 subscribers

47,162 Aufrufe • vor 1 Monat •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Dario Amodei says the spark was seeing engineers stop writing code and start supervising it. Inside Anthropic, Claude writes much of the software, and humans review like editors. The twist is meta: some of that code helps build the next Claude. That’s the self-improvement loop tightening, says Dario Amodei.
0:49

Dario Amodei says the spark was seeing engineers stop writing code and start supervising it. Inside Anthropic, Claude writes much of the software, and humans review like editors. The twist is meta: some of that code helps build the next Claude. That’s the self-improvement loop tightening, says Dario Amodei.

Wes Roth

87,585 Aufrufe • vor 4 Monaten

We've been tracking AI code review tools across OSS, and a new category is emerging. We're calling it "Deep Review": → Standard AI review: PR-level, fast, human in the loop → Deep Review: repo-wide context, runs autonomously in the background 🧵👇
0:26

We've been tracking AI code review tools across OSS, and a new category is emerging. We're calling it "Deep Review": → Standard AI review: PR-level, fast, human in the loop → Deep Review: repo-wide context, runs autonomously in the background 🧵👇

Martian

39,916 Aufrufe • vor 2 Monaten

Introducing Code Review Bench v0: The first independent code review benchmark. 200,000+ PRs. Unbiased. Fully OSS. Updated daily. Tool performance highlights 🧵👇 Featuring: Augment Code baz Claude CodeRabbit Cursor Google Gemini GitHub Graphite Greptile Kilo OpenAI Developers Propel Qodo
1:59

Introducing Code Review Bench v0: The first independent code review benchmark. 200,000+ PRs. Unbiased. Fully OSS. Updated daily. Tool performance highlights 🧵👇 Featuring: Augment Code baz Claude CodeRabbit Cursor Google Gemini GitHub Graphite Greptile Kilo OpenAI Developers Propel Qodo

Martian

218,722 Aufrufe • vor 3 Monaten

LIGHTS OUT! That is the future of software factories says @MVanHorn. The rules: no code to be written by humans, no code to be reviewed by humans. PERIOD! How long before we have software companies with human OUT of the loop?
4:07

LIGHTS OUT! That is the future of software factories says @MVanHorn. The rules: no code to be written by humans, no code to be reviewed by humans. PERIOD! How long before we have software companies with human OUT of the loop?

This Week in Startups

393,745 Aufrufe • vor 3 Monaten

GitHub CEO Thomas Dohmke (Thomas Dohmke) confirmed in conversation with me what many suspected but few wanted to say out loud: we've already crossed the threshold where AI generates code faster than humans can meaningfully review it. The era of human oversight in software development is already over.
0:57

GitHub CEO Thomas Dohmke (Thomas Dohmke) confirmed in conversation with me what many suspected but few wanted to say out loud: we've already crossed the threshold where AI generates code faster than humans can meaningfully review it. The era of human oversight in software development is already over.

Azeem Azhar

49,534 Aufrufe • vor 1 Jahr

And we're live!! Still think Sonnet 3.7 is the best model at writing and reviewing code? Try yourself - Contribute to the first human leaderboard for code review - We'll crown the first model to get to 1000 wins as the best PR review model 🏆
1:32

And we're live!! Still think Sonnet 3.7 is the best model at writing and reviewing code? Try yourself - Contribute to the first human leaderboard for code review - We'll crown the first model to get to 1000 wins as the best PR review model 🏆

Aiswarya Sankar

32,142 Aufrufe • vor 1 Jahr

Today we're launching REVIEW.FAST, speeding up human review of AI generated code 3X. AI changed the world, sped up writing code, but shifted the bottleneck to review. If you can speed up code review, you can ship more. It's as simple as that.
1:37

Today we're launching REVIEW.FAST, speeding up human review of AI generated code 3X. AI changed the world, sped up writing code, but shifted the bottleneck to review. If you can speed up code review, you can ship more. It's as simple as that.

Louis Knight-Webb

45,945 Aufrufe • vor 5 Monaten

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)
0:34

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 Aufrufe • vor 11 Monaten

Stage is a code review platform designed to help engineers understand AI-generated code. Your team is drowning in an endless backlog of PRs. Stage turns code review into a guided process and enables you to review changes faster than using GitHub. Congrats on the launch, Charles Pan and Dean Stratakos!
0:50

Stage is a code review platform designed to help engineers understand AI-generated code. Your team is drowning in an endless backlog of PRs. Stage turns code review into a guided process and enables you to review changes faster than using GitHub. Congrats on the launch, Charles Pan and Dean Stratakos!

Y Combinator

1,062,430 Aufrufe • vor 18 Tagen

I stopped using the same AI to write and review code. Claude builds. GPT-5.2 Codex reviews. Result? More bugs caught, real security issues flagged, and better PRs all automated.
6:33

I stopped using the same AI to write and review code. Claude builds. GPT-5.2 Codex reviews. Result? More bugs caught, real security issues flagged, and better PRs all automated.

Mervin Praison

10,891 Aufrufe • vor 4 Monaten

Claude Code on desktop can now preview your running apps, review your code, and handle CI failures and PRs in the background. Here’s what's new:
1:15

Claude Code on desktop can now preview your running apps, review your code, and handle CI failures and PRs in the background. Here’s what's new:

Claude

9,308,779 Aufrufe • vor 3 Monaten

The bottleneck in coding is now the time it takes a human to review agent-generated code. But existing review UIs don't work well for agents. So we built a new one into Amp.
2:15

The bottleneck in coding is now the time it takes a human to review agent-generated code. But existing review UIs don't work well for agents. So we built a new one into Amp.

Beyang

62,900 Aufrufe • vor 7 Monaten

I asked Simon Willison what the next leap in AI software engineering is likely to be. He explained the "dark factory" pattern where teams don't write any code or even look at their code.
0:53

I asked Simon Willison what the next leap in AI software engineering is likely to be. He explained the "dark factory" pattern where teams don't write any code or even look at their code.

Lenny Rachitsky

69,856 Aufrufe • vor 2 Monaten

Claude Code Desktop can now run your app, catch errors, review code, and merge PRs automatically 🤯 This update closes the entire development loop — from writing to previewing to reviewing to fixing to merging — without you lifting a finger. Want the full guide? DM me.
0:41

Claude Code Desktop can now run your app, catch errors, review code, and merge PRs automatically 🤯 This update closes the entire development loop — from writing to previewing to reviewing to fixing to merging — without you lifting a finger. Want the full guide? DM me.

Julian Goldie SEO

12,984 Aufrufe • vor 3 Monaten

After reaching AI-native terminal velocity we are swamped in code review. The core insight is that as long as you can write code in parallel you will continue to be stuck until you can review it in parallel. I was surprised by how quickly this became my daily driver for not just review code, but writing it as well.
0:30

After reaching AI-native terminal velocity we are swamped in code review. The core insight is that as long as you can write code in parallel you will continue to be stuck until you can review it in parallel. I was surprised by how quickly this became my daily driver for not just review code, but writing it as well.

Evan Boyle

23,954 Aufrufe • vor 4 Monaten

This is the future of terminals!!! Tell the terminal what to do in English and let it execute the commands for you. No need to search for and remember esoteric commands anymore. Create projects from scratch, review your PRs and start projects simply by using English. Warp 🤖 takes the terminal to the next level. 1. Review code changes This prompt reviews my code changes before pushing them to the remote branch. It even takes parameters for extra context such as: - my coding style guide - the existing pull request link - the technologies used
1:03

This is the future of terminals!!! Tell the terminal what to do in English and let it execute the commands for you. No need to search for and remember esoteric commands anymore. Create projects from scratch, review your PRs and start projects simply by using English. Warp 🤖 takes the terminal to the next level. 1. Review code changes This prompt reviews my code changes before pushing them to the remote branch. It even takes parameters for extra context such as: - my coding style guide - the existing pull request link - the technologies used

Catalin

32,199 Aufrufe • vor 1 Jahr

Dario Amodei just told software engineers exactly how long they have. Six to twelve months. Amodei: “I have engineers within Anthropic who say I don’t write any code anymore. I just let the model write the code, I edit it, I do the things around it.” The people building the most powerful AI in history have already stopped writing code. That is not a forecast. That is the current working condition inside the lab closest to the frontier. Amodei: “We might be six to 12 months away from when the model is doing most, maybe all, of what SWEs do end-to-end.” The tech industry spent a decade making software engineers its highest-paid, most protected class. That era has a last day now. When a model can execute an entire software build end-to-end, the ability to write syntax stops being a skill. It becomes a credential for a job that no longer exists. Amodei: “And then it’s a question of how fast does that loop close.” That is the sentence everyone skipped. The code was never the hard part. The hard part was everything around it. The model just learned everything around it. Writing the code is already nearly gone. Testing is next. Deployment is next. When all three collapse into a single autonomous execution loop, the machine no longer needs a human in the chain at all. The corporation or sovereign state that closes that loop first does not gain a competitive advantage. It gains a category of speed that biological engineers cannot match, track, or reverse. That is not disruption. That is replacement at a systems level. Amodei is not describing a future disruption. He is describing the current state of his own building. The loop is already closing. The only question is whether you are inside it or outside it when it seals.
0:27

Dario Amodei just told software engineers exactly how long they have. Six to twelve months. Amodei: “I have engineers within Anthropic who say I don’t write any code anymore. I just let the model write the code, I edit it, I do the things around it.” The people building the most powerful AI in history have already stopped writing code. That is not a forecast. That is the current working condition inside the lab closest to the frontier. Amodei: “We might be six to 12 months away from when the model is doing most, maybe all, of what SWEs do end-to-end.” The tech industry spent a decade making software engineers its highest-paid, most protected class. That era has a last day now. When a model can execute an entire software build end-to-end, the ability to write syntax stops being a skill. It becomes a credential for a job that no longer exists. Amodei: “And then it’s a question of how fast does that loop close.” That is the sentence everyone skipped. The code was never the hard part. The hard part was everything around it. The model just learned everything around it. Writing the code is already nearly gone. Testing is next. Deployment is next. When all three collapse into a single autonomous execution loop, the machine no longer needs a human in the chain at all. The corporation or sovereign state that closes that loop first does not gain a competitive advantage. It gains a category of speed that biological engineers cannot match, track, or reverse. That is not disruption. That is replacement at a systems level. Amodei is not describing a future disruption. He is describing the current state of his own building. The loop is already closing. The only question is whether you are inside it or outside it when it seals.

Dustin

315,019 Aufrufe • vor 3 Monaten

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."
1:12

"The one thing that's going to be truly future proof is judgment. What is the biggest challenge when you have a thousand AI engineers writing code? AI slop. In an era when you can do everything, the question is which of these things matter. On the engineer side, it is evaluating the code. Which of this code is even valuable? You can have AI engineers writing beautiful code that could be wrong, that could have bugs in it, that could be vulnerable. Someone needs to review it. Make sure to have a human review at some point, especially critical code that is in the core of your system. On the product side is judgment around what needs to be built and evaluating. And similarly in design, you have to have judgment around, does it make sense in the broader design system. I think this judgment is the number one thing that humans are going to bring in an era of infinite productivity."

Patrick OShaughnessy

24,818 Aufrufe • vor 4 Monaten

👀 Ever want a second set of eyes on your code? GitHub Copilot code review can help! Available in preview, Copilot code review offers fast, AI-powered feedback on your code as you write it. You can quickly apply any feedback that Copilot suggests, directly in the editor.
0:26

👀 Ever want a second set of eyes on your code? GitHub Copilot code review can help! Available in preview, Copilot code review offers fast, AI-powered feedback on your code as you write it. You can quickly apply any feedback that Copilot suggests, directly in the editor.

Visual Studio Code

75,224 Aufrufe • vor 1 Jahr

Review code written by one agent using a different agent entirely. Here, Claude handles the task, and Gemini runs the review, leaves inline comments, and sends them back to the original agent to implement. Any combination works.
0:39

Review code written by one agent using a different agent entirely. Here, Claude handles the task, and Gemini runs the review, leaves inline comments, and sends them back to the original agent to implement. Any combination works.

Air by JetBrains

19,476,873 Aufrufe • vor 1 Monat