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。

Astra (GPT-6) is a full-stack developer that can finish coding work, then verify output, then mark linear tickets as done using your own hardware It's so over

Mehul Mohan

33,464 subscribers

47,350 次观看 • 1 个月前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

26 条评论

Aditya Vyas 的头像

Aditya Vyas1 个月前

People will abuse it for it's boring mistakes. In 3-6 weeks we will get a Chinese model doing the same. See you later on that side.

shydev 的头像

shydev1 个月前

slop. why is it using ui to do all that? can't it use linear mcp.

Webster | JARVIS 的头像

Webster | JARVIS1 个月前

bro just let me have my job for another year 💀

Niraj Adhikari 的头像

Niraj Adhikari1 个月前

how is it over?

AbhiiinavCodes 的头像

AbhiiinavCodes1 个月前

Why are they even building such things? Money makes the only reason for such shit. You aren't giving clarity on future and just going on with AI disrupting most of the roles. They aren't innovators but destroyers

yagodnyi 的头像

yagodnyi1 个月前

5.6 can do it too

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

closing tickets on its own is wild

Patch Goblin 的头像

Patch Goblin1 个月前

Every tweet with this it's over bullshit is plain bullshit.

VOID 的头像

VOID1 个月前

Dunno whether you will find this hilarious or concerning! LOL! -

Priya 的头像

Priya1 个月前

But it wouldn't pay my AWS bill from open AI wallet.

Hitesh Sharma 的头像

Hitesh Sharma1 个月前

The "its over" click bait has been there since the days of Devin launch. Nothing got over yet, rather we got hell lot of things to upskill on. The best it did is gaining a few more followers forthe one claiming "its over"

Ned 的头像

Ned1 个月前

Now sell it and report back.

Nick Thorp 的头像

Nick Thorp1 个月前

This is exactly what happened with early “close the Jira ticket” agents: they passed unit tests, marked done, and missed the product case that only showed up in staging.

Jay Zhou 的头像

Jay Zhou1 个月前

A model that codes, verifies, and closes tickets is a staffing change. The remaining job is deciding which tickets should exist.

TAL77SVAD 的头像

TAL77SVAD1 个月前

#LosersUseAI L O S E R S

⭕ Sai Bharadwaj 🦞⚡️ 的头像

⭕ Sai Bharadwaj 🦞⚡️1 个月前

final nail.

Aditya 的头像

Aditya1 个月前

What is it, so over? Marking linear tickets as done?

Aastha Sahu 的头像

Aastha Sahu1 个月前

the verify step is the whole claim rly. does it actually catch its own broken output or does it just mark the ticket done and move on

AIA 的头像

AIA1 个月前

Ab Krna kya hai, ye v to bataoo🙊🙈??

Md Jaoyad 的头像

Md Jaoyad1 个月前

Agentic AI with new dimension ❤️

Navin Kumar Yadav 的头像

Navin Kumar Yadav1 个月前

How reliable is it on bigger tasks? I’m curious where it starts needing human review instead of fully finishing the ticket on its own.

Deepraj 的头像

Deepraj1 个月前

Finishes the ticket and closes Linear on your box. That's not a model drop. That's a junior with a receipt.

Flaude Cable 的头像

Flaude Cable1 个月前

Overhyped bullshit. Just 3% more than fable on deepswe.

Prajwal 的头像

Prajwal1 个月前

Ye to mera current setup bhi krta h

Jarno 的头像

Jarno1 个月前

Marking the ticket done is the easy part. Real test is whether it catches its own regressions before you do.

Sanjay Raj Sharma 的头像

Sanjay Raj Sharma1 个月前

😂

相关视频

GPT 6 Astra × GPT Image 2.5 is a killer combination. I used @/sketch to draw a fighter jet. GPT Image 2.5 turned the sketch into a realistic image. Then GPT 6 Astra turned that image into a 3D model in Blender.

GPT 6 Astra × GPT Image 2.5 is a killer combination. I used @/sketch to draw a fighter jet. GPT Image 2.5 turned the sketch into a realistic image. Then GPT 6 Astra turned that image into a 3D model in Blender.

Karan

10,243 次观看 • 1 个月前

🚨 GPT-6 Sol Second Output Got LEAKED The output looks absolutely insane This kind of quality is terrifying It beats GPT-6 Astra in coding and frontend generation and it will be a lot cheaper OpenAI have left Anthropic FAR behind

🚨 GPT-6 Sol Second Output Got LEAKED The output looks absolutely insane This kind of quality is terrifying It beats GPT-6 Astra in coding and frontend generation and it will be a lot cheaper OpenAI have left Anthropic FAR behind

Salio

408,814 次观看 • 1 个月前

I built an ancient Indian kingdom in Three.js using Gpt 6 Astra then handed the footage to Seedance 2.5 The top is the world created by Gpt 6 Astra The bottom is how AI reimagined it

I built an ancient Indian kingdom in Three.js using Gpt 6 Astra then handed the footage to Seedance 2.5 The top is the world created by Gpt 6 Astra The bottom is how AI reimagined it

Karan

18,333 次观看 • 1 个月前

GPT-6 Astra at launch vs GPT-6 Astra today. Identical prompt. Same settings. Today's output is clearly weaker. Not saying it's been nerfed, but something has definitely changed. Anyone else seeing this?

GPT-6 Astra at launch vs GPT-6 Astra today. Identical prompt. Same settings. Today's output is clearly weaker. Not saying it's been nerfed, but something has definitely changed. Anyone else seeing this?

Trinks | Making Alerith

285,798 次观看 • 1 个月前

i finally cracked how to master GPT-6 Astra OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster Most people are still prompting Astra like GPT-5. That's the mistake. Bookmark this, then read the article below to build to alpha trading strategies 24/7

i finally cracked how to master GPT-6 Astra OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster Most people are still prompting Astra like GPT-5. That's the mistake. Bookmark this, then read the article below to build to alpha trading strategies 24/7

Roan

70,606 次观看 • 1 个月前

GPT-6 Astra is a beast!! 😳😳 My 10-year-old just built a 3D rocket game using GPT-6 Astra 🚀

GPT-6 Astra is a beast!! 😳😳 My 10-year-old just built a 3D rocket game using GPT-6 Astra 🚀

Hardik Shah

15,818 次观看 • 1 个月前

Simpsons Hit and Run reversed engineered from the PS2 game and then rebuilt for web using three.js. This was all done by the amazing GPT-6 Astra model on xhigh reasoning (used a lot of my usage to do this). Best part is it's open source:

Simpsons Hit and Run reversed engineered from the PS2 game and then rebuilt for web using three.js. This was all done by the amazing GPT-6 Astra model on xhigh reasoning (used a lot of my usage to do this). Best part is it's open source:

Dwayne

1,118,476 次观看 • 1 个月前

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

OPENAI JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING GPT-6 ASTRA This is the most important prompting update for anyone using Astra. Bookmark this before your next build. Most people are still prompting Astra like GPT-5. That's the mistake. → audit your AGENTS.md — old instructions now fight the model → define autonomy explicitly — Astra pauses when you expect it to continue → cut skill descriptions to one line — too many skills and Astra sees none of them clearly → stop telling it to run tests — it does this automatically, repeating it causes overtesting → define stop conditions — Astra needs to know what "done" means Astra is at its best when you stop micromanaging and let it own the work. Read the full guide before writing your next prompt. GPT-6 Astra → Clean System Prompt → Autonomous Execution → Production-Ready Output → Ship faster

Rahul

363,389 次观看 • 1 个月前

Every FREE path to GPT-6 Astra I can still verify today: > Experiential Labs: GPT-6 Astra + Fable 5.1 on the free promo row ($0/$0). Pick the model, start chatting: > v0: GPT-6 Astra in the model picker (Google signup). All-models access is time-boxed, then Free drops to Mini: > Venice: anonymous try with welcome credits. Burns fast at Astra rates. Not unlimited free: Three free paths. Grab them while the promos last. Steps in the video.

Every FREE path to GPT-6 Astra I can still verify today: > Experiential Labs: GPT-6 Astra + Fable 5.1 on the free promo row ($0/$0). Pick the model, start chatting: > v0: GPT-6 Astra in the model picker (Google signup). All-models access is time-boxed, then Free drops to Mini: > Venice: anonymous try with welcome credits. Burns fast at Astra rates. Not unlimited free: Three free paths. Grab them while the promos last. Steps in the video.

ＺＥＦＩ

21,916 次观看 • 1 个月前

GPT-6 Astra vibe-coded a playable chase and put it online right away. From a single prompt it wrote the car physics, the police behavior, the traffic, the checkpoints and the scoring, then brought the whole thing up at a live link. That is what AGI looks like at work. Made with Higgsfield + GPT-6 Astra.

GPT-6 Astra vibe-coded a playable chase and put it online right away. From a single prompt it wrote the car physics, the police behavior, the traffic, the checkpoints and the scoring, then brought the whole thing up at a live link. That is what AGI looks like at work. Made with Higgsfield + GPT-6 Astra.

Higgsfield AI 🧩

12,524 次观看 • 1 个月前

Common Linear workflow we have internally: from Slack message to merged code in minutes. User asked about MCP team docs support, Linear agent checked the code to verify if it's true then started coding session to add it. Code was then reviewed, improve and merged through Diffs.

Common Linear workflow we have internally: from Slack message to merged code in minutes. User asked about MCP team docs support, Linear agent checked the code to verify if it's true then started coding session to add it. Code was then reviewed, improve and merged through Diffs.

Karri Saarinen

31,732 次观看 • 4 个月前

GPT-6 Astra is state-of-the-art on: 🌟 Computer use 🌟 Browsing 🌟 Agentic coding 🌟 Cybersecurity 🌟 Science 🌟 Professional work

GPT-6 Astra is state-of-the-art on: 🌟 Computer use 🌟 Browsing 🌟 Agentic coding 🌟 Cybersecurity 🌟 Science 🌟 Professional work

ChatGPT

1,534,390 次观看 • 1 个月前

GPT-6.1 Terra continues to advance the cost-intelligence frontier across our model families. It’s a significant step up over GPT‑5.6 Terra, with 50% lower standard API prices. In ChatGPT Work and Codex, your usage allowance goes further with GPT‑6.1 Terra than with GPT‑5.6 Terra—and far more than with GPT‑6.1 Sol or GPT‑6 Astra. For in-depth research or complex coding, choose GPT-6.1 Sol or GPT-6 Astra.

GPT-6.1 Terra continues to advance the cost-intelligence frontier across our model families. It’s a significant step up over GPT‑5.6 Terra, with 50% lower standard API prices. In ChatGPT Work and Codex, your usage allowance goes further with GPT‑6.1 Terra than with GPT‑5.6 Terra—and far more than with GPT‑6.1 Sol or GPT‑6 Astra. For in-depth research or complex coding, choose GPT-6.1 Sol or GPT-6 Astra.

OpenAI

476,772 次观看 • 5 天前

Using GPT-6 Astra I was able to quickly protorype a sparse grid allocator fluid simulation for VRChat using my specified architecture, but honestly as cool as it is its absolutely overkill for VRChat. Isosurface ray tracing could be done here, but its too complex to work with.

Using GPT-6 Astra I was able to quickly protorype a sparse grid allocator fluid simulation for VRChat using my specified architecture, but honestly as cool as it is its absolutely overkill for VRChat. Isosurface ray tracing could be done here, but its too complex to work with.

Mykhailo Moroz

41,365 次观看 • 1 个月前

This is GPT-6 Astra. Anything you can do on a computer, Astra can do for you. Fast.

This is GPT-6 Astra. Anything you can do on a computer, Astra can do for you. Fast.

OpenAI

139,005,137 次观看 • 1 个月前

GPT Astra output

GPT Astra output

Dr Singularity

12,803 次观看 • 2 个月前

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

Stefan 3D AI

471,023 次观看 • 1 个月前

It's so over guys Astra is doing AI CAD at such a fast speed that the model just materializes before I can even finish typing the prompt. WOW

It's so over guys Astra is doing AI CAD at such a fast speed that the model just materializes before I can even finish typing the prompt. WOW

Kyle Cothern

25,787 次观看 • 1 个月前

OpenAI People after using GPT-6 Astra

OpenAI People after using GPT-6 Astra

Thomas Unise

174,646 次观看 • 1 个月前

🚨 GPT-Astra first output Got LEAKED GPT-Astra is dropping today and This early output is seriously impressive GPT-Astra is absolutely mogging Fable 5.1 in game generation🔥 And this is just one early leak… OpenAI might be cooking Today

🚨 GPT-Astra first output Got LEAKED GPT-Astra is dropping today and This early output is seriously impressive GPT-Astra is absolutely mogging Fable 5.1 in game generation🔥 And this is just one early leak… OpenAI might be cooking Today

Salio

69,255 次观看 • 1 个月前