nader dabit's banner

nader dabit

@dabit3 • 196,438 subscribers

Growth @cognition @devindevelopers @devinai

Shorts

Fusion is the most efficient frontier harness for GPT 6 Astra and Claude Fable 5.1. You can also configure everything about it: • Base model: Fable, Astra, Sol, or Opus • Sidekick model: SWE (Free), Luna, Sol, GLM (Free) • Speed: Normal or Fast ⚡ • Reasoning level It retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs and is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index! Importantly: it's also fun to use :)

Fusion is the most efficient frontier harness for GPT 6 Astra and Claude Fable 5.1. You can also configure everything about it: • Base model: Fable, Astra, Sol, or Opus • Sidekick model: SWE (Free), Luna, Sol, GLM (Free) • Speed: Normal or Fast ⚡ • Reasoning level It retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs and is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index! Importantly: it's also fun to use :)

805,827 просмотров

Steer Cloud Agents from the CLI (not just on Web). ssh directly into it. PRs tested in a real VM, real browser / devices, and on video. ☁️ Free SWE-2 until October 8. No reason not to try it out!

Steer Cloud Agents from the CLI (not just on Web). ssh directly into it. PRs tested in a real VM, real browser / devices, and on video. ☁️ Free SWE-2 until October 8. No reason not to try it out!

503,062 просмотров

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

433,658 просмотров

Another crazy TypeSafe AI Jev example: Predictive spreadsheets Spreadsheets recalculate numbers, not meaning. Jev reads intent. Type "Urgency" at the top of a column and, as you type, it figures out you want each row rated from "no follow-up needed" to "urgent" in ~100 ms.

Another crazy TypeSafe AI Jev example: Predictive spreadsheets Spreadsheets recalculate numbers, not meaning. Jev reads intent. Type "Urgency" at the top of a column and, as you type, it figures out you want each row rated from "no follow-up needed" to "urgent" in ~100 ms.

277,424 просмотров

1,200% more speed with little tradeoff in intelligence. If you value your time it's worth experimenting at the Pareto frontier of speed with models like SWE-1.7 Lightning (1,000 tok/s).

1,200% more speed with little tradeoff in intelligence. If you value your time it's worth experimenting at the Pareto frontier of speed with models like SWE-1.7 Lightning (1,000 tok/s).

192,811 просмотров

1,000 tok/s vs 85 tok/s visualized

1,000 tok/s vs 85 tok/s visualized

212,315 просмотров

We rolled out support for GLM 5.3 Flash along with an improved model picker UX in Devin CLI. ⚡ Devin now supports: GLM-5.3, 5.3 Flash, 5.2 Claude Fable, Haiku, Opus, Sonnet GPT-5.6 Sol, Luna, Terra + others DeepSeek V4 Flash, Pro SWE-1.7, 1.6 Gemini 3.7 Flash Grok 4.6, 4.5 Inkling Kimi K3, 2.7 + others Also available in Devin Desktop.

We rolled out support for GLM 5.3 Flash along with an improved model picker UX in Devin CLI. ⚡ Devin now supports: GLM-5.3, 5.3 Flash, 5.2 Claude Fable, Haiku, Opus, Sonnet GPT-5.6 Sol, Luna, Terra + others DeepSeek V4 Flash, Pro SWE-1.7, 1.6 Gemini 3.7 Flash Grok 4.6, 4.5 Inkling Kimi K3, 2.7 + others Also available in Devin Desktop.

91,215 просмотров

Outposts are a killer new feature that let you run Devin sessions on your own machines. Devin's brain stays in the cloud, but every command and file edit executes on infrastructure you control.

Outposts are a killer new feature that let you run Devin sessions on your own machines. Devin's brain stays in the cloud, but every command and file edit executes on infrastructure you control.

152,613 просмотров

we're about to build so much saas

we're about to build so much saas

69,737 просмотров

Beautiful UX enhancements shipped to Devin. One of my favorites is the visualization of child sessions in the nav. Worth emphasizing what these are: not subagents sharing your session's context, but full Devins in isolated VMs. Each executes and verifies its own work while the coordinator integrates results.

Beautiful UX enhancements shipped to Devin. One of my favorites is the visualization of child sessions in the nav. Worth emphasizing what these are: not subagents sharing your session's context, but full Devins in isolated VMs. Each executes and verifies its own work while the coordinator integrates results.

55,550 просмотров

GPT-6 Astra now available in Devin CLI and Devin Desktop.

GPT-6 Astra now available in Devin CLI and Devin Desktop.

45,903 просмотров

I agree that agents integrated into team environments is the next paradigm in LLM UIUX but I'd take it a step further and argue that you shouldn't have to even tag your agent. Agents should be smart enough to know when to do work, just like a human.

I agree that agents integrated into team environments is the next paradigm in LLM UIUX but I'd take it a step further and argue that you shouldn't have to even tag your agent. Agents should be smart enough to know when to do work, just like a human.

56,768 просмотров

notion 1-shotted in ~30 minutes with Fable + Devin

notion 1-shotted in ~30 minutes with Fable + Devin

56,823 просмотров

this is not sped up. Cognition SWE-1.6 is just moving fast enough that the interaction feels like a different product category the nice thing about a model this fast is you stop treating it like a task runner and start treating it like something you can actually riff with!

this is not sped up. Cognition SWE-1.6 is just moving fast enough that the interaction feels like a different product category the nice thing about a model this fast is you stop treating it like a task runner and start treating it like something you can actually riff with!

12,807 просмотров

Devin lets you scrub, rewind, and replay agent sessions. Useful when running parallel agents, background agents, or scheduled sessions / cron jobs.

Devin lets you scrub, rewind, and replay agent sessions. Useful when running parallel agents, background agents, or scheduled sessions / cron jobs.

13,945 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Devin can now build and test iPhone Duo apps in macOS cloud VMs Unfold the phone, fold it, close it, check every screen, and get video verification of everything. Here are some examples: 1. Devin takes someone's portrait while they watch themselves on the outside screen, it sends posing cues, half-folds the phone so it stands on a table, takes timer shots, and closes the phone mid-countdown to make sure no photo gets lost

Devin can now build and test iPhone Duo apps in macOS cloud VMs Unfold the phone, fold it, close it, check every screen, and get video verification of everything. Here are some examples: 1. Devin takes someone's portrait while they watch themselves on the outside screen, it sends posing cues, half-folds the phone so it stands on a table, takes timer shots, and closes the phone mid-countdown to make sure no photo gets lost

240,746 просмотров • 2 дней назад

Automated UI testing feels like AGI in Devin 10 examples (running macOS + Linux Cloud Agents) 🧵 What happens (automatic for any update): • Creates programmatic test plan • Boots the app with secrets & credentials (auth, etc.) • Autonomously clicks, types, and checks the UI like a human using a computer would • Records a test • Edits the video, attaches step by step walkthrough of the actions it took • Sends you a concise video artifact As we move away from reading every line of code, new advanced ways of testing become more valuable. 1. Testing a platform for signing documents electronically

Automated UI testing feels like AGI in Devin 10 examples (running macOS + Linux Cloud Agents) 🧵 What happens (automatic for any update): • Creates programmatic test plan • Boots the app with secrets & credentials (auth, etc.) • Autonomously clicks, types, and checks the UI like a human using a computer would • Records a test • Edits the video, attaches step by step walkthrough of the actions it took • Sends you a concise video artifact As we move away from reading every line of code, new advanced ways of testing become more valuable. 1. Testing a platform for signing documents electronically

1,603,475 просмотров • 1 месяц назад

Devin's VM is your dev box. `devin ssh` drops you straight into the environment Devin is working in. macOS, Linux, Windows, you can just treat it like a server. Because you also have access to Devin, the design space is big. Here's a look at what you can do:

Devin's VM is your dev box. `devin ssh` drops you straight into the environment Devin is working in. macOS, Linux, Windows, you can just treat it like a server. Because you also have access to Devin, the design space is big. Here's a look at what you can do:

553,911 просмотров • 24 дней назад

Devin now has a Mac  Here are 11 experiments I've run over the past week, as well as open source code for over 100 more native apps. Build, test, deploy iOS, iPad, and macOS apps in the cloud with just a prompt. ⚡ 1. Build and test a multi-platform, multiplayer app in the cloud (iOS, iPad, web)

Devin now has a Mac  Here are 11 experiments I've run over the past week, as well as open source code for over 100 more native apps. Build, test, deploy iOS, iPad, and macOS apps in the cloud with just a prompt. ⚡ 1. Build and test a multi-platform, multiplayer app in the cloud (iOS, iPad, web)

733,775 просмотров • 1 месяц назад

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

433,658 просмотров • 1 месяц назад

My favorite thing about Devin Mobile app is that I can control fleets of Macs in the cloud to build and test native iOS apps from literally anywhere 🤯

My favorite thing about Devin Mobile app is that I can control fleets of Macs in the cloud to build and test native iOS apps from literally anywhere 🤯

206,913 просмотров • 20 дней назад

Made a short video walking through Devin Mobile: Cloud agents running on Linux, MacOS, or Windows from anywhere

Made a short video walking through Devin Mobile: Cloud agents running on Linux, MacOS, or Windows from anywhere

62,033 просмотров • 11 дней назад

Something I wanted to see if Claude Opus 4.5 could do: clone a fully functional Billion $ SAAS product and make it at least 100x cheaper. The first product that came to mind was TypeForm because it's very popular, very expensive, and in theory, very simple. The result is OpenForm: a polished + functional and Open Source Typeform clone at ~100x less cost, that can be setup and deployed in ~15 minutes. The agent building this ran for ~35 minutes. Here are the details, technique, and the code:

Something I wanted to see if Claude Opus 4.5 could do: clone a fully functional Billion $ SAAS product and make it at least 100x cheaper. The first product that came to mind was TypeForm because it's very popular, very expensive, and in theory, very simple. The result is OpenForm: a polished + functional and Open Source Typeform clone at ~100x less cost, that can be setup and deployed in ~15 minutes. The agent building this ran for ~35 minutes. Here are the details, technique, and the code:

1,828,761 просмотров • 9 месяцев назад

You can automate pixel-perfect product tutorials with a cloud agent that has its own computer and records itself using your app the way a human would (like Devin). This has technically been possible for a while, but with Opus 5.5 the results have progressed to something better than what I make by hand. Devin even made a tutorial showing you how it's done:

You can automate pixel-perfect product tutorials with a cloud agent that has its own computer and records itself using your app the way a human would (like Devin). This has technically been possible for a while, but with Opus 5.5 the results have progressed to something better than what I make by hand. Devin even made a tutorial showing you how it's done:

110,027 просмотров • 20 дней назад

Jev is really good at intent-based search! How it looks in Gmail: (for a huge inbox you'd prob let semantic search / embeddings pull first but still much better experience)

Jev is really good at intent-based search! How it looks in Gmail: (for a huge inbox you'd prob let semantic search / embeddings pull first but still much better experience)

135,219 просмотров • 1 месяц назад

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

304,018 просмотров • 2 месяцев назад

Today we shipped Memory and Dreaming in Devin: persistent self-cleaning memory for agent sessions. The standard is OSS and also works across any harness in any environment. ⚡

Today we shipped Memory and Dreaming in Devin: persistent self-cleaning memory for agent sessions. The standard is OSS and also works across any harness in any environment. ⚡

46,897 просмотров • 12 дней назад

I used the X Algorithm to build insidetheforyou Experience how X interactions affect your future feed using real posts + data & lets you design an algorithm feat Cognition Hybrid 🏃🏾 Kent C. Dodds 🐨 Theo - t3.gg maria Ryan Carson Jared Zoneraich Jared Palmer ++

I used the X Algorithm to build insidetheforyou Experience how X interactions affect your future feed using real posts + data & lets you design an algorithm feat Cognition Hybrid 🏃🏾 Kent C. Dodds 🐨 Theo - t3.gg maria Ryan Carson Jared Zoneraich Jared Palmer ++

208,136 просмотров • 2 месяцев назад

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!

Devin Cloud Agents can now build and ship a real macOS release end-to-end, all in a real Mac environment (with full computer use). In this demo, the agent builds a native SwiftUI app, code-signs it, notarizes with Apple via notarytool, staples the ticket, and packages a signed DMG with the classic drag-to-Applications window. With computer use, it installs its own app like a real user: mount, drag, eject, launch with zero Gatekeeper warnings. It even verified notifications fired by checking the macOS notification database on screen, with a full recording and release report delivered for review. This entire workflow now takes about 60 seconds to spin up and tear down with Devin and Namespace. You can choose multiple versions of macOS of Xcode for your environment!

147,071 просмотров • 2 месяцев назад

1,000 tok/s, SWE-1.7 is near-frontier intelligence at real-time speed. Building this way is a new category of DX. A task that used to justify walking away finishes before you've mentally moved on. There's a weird middle mode now: it's technically async, but fast enough that you just... watch. In this example I'm running it head to head with GLM-5.2 Max. • SWE-1.7 is now free in Devin CLI or Desktop • SWE-1.7 Fast (Lightning mode) is $2.5 / MTok In · $12.5 / MTok Out

1,000 tok/s, SWE-1.7 is near-frontier intelligence at real-time speed. Building this way is a new category of DX. A task that used to justify walking away finishes before you've mentally moved on. There's a weird middle mode now: it's technically async, but fast enough that you just... watch. In this example I'm running it head to head with GLM-5.2 Max. • SWE-1.7 is now free in Devin CLI or Desktop • SWE-1.7 Fast (Lightning mode) is $2.5 / MTok In · $12.5 / MTok Out

178,914 просмотров • 3 месяцев назад

Simple mental model for cloud agents: clone the exact state of your laptop, multiply it infinitely, and make it accessible via HTTP. Most people still don't know cloud agents can spin up full Linux, Windows, Android, etc.. environments on demand, run computer-use tests, record annotated video proof of your app working through updates, drive Playwright against live Chrome with persistent auth, all triggerable from anywhere. Here I'm experimenting with a fork of Nous Research Hermes Agent built specifically on low latency. I've set up a Devin automation that checks Hermes daily for upstream changes, implements the updates, runs tests to make sure it works, sends me proof that it does, creates a PR, and reviews it. All I have to do to keep the fork up to date is review the daily morning PR.

Simple mental model for cloud agents: clone the exact state of your laptop, multiply it infinitely, and make it accessible via HTTP. Most people still don't know cloud agents can spin up full Linux, Windows, Android, etc.. environments on demand, run computer-use tests, record annotated video proof of your app working through updates, drive Playwright against live Chrome with persistent auth, all triggerable from anywhere. Here I'm experimenting with a fork of Nous Research Hermes Agent built specifically on low latency. I've set up a Devin automation that checks Hermes daily for upstream changes, implements the updates, runs tests to make sure it works, sends me proof that it does, creates a PR, and reviews it. All I have to do to keep the fork up to date is review the daily morning PR.

122,370 просмотров • 3 месяцев назад

High ROI skill: driving 24/7 app maintenance + engineering automations, and a key component of a real software factory. Implementing these workflows is simpler than ever, you just need clear language. Here are 4 workflows and 40+ more you can build in ~1 minute each 🧵

High ROI skill: driving 24/7 app maintenance + engineering automations, and a key component of a real software factory. Implementing these workflows is simpler than ever, you just need clear language. Here are 4 workflows and 40+ more you can build in ~1 minute each 🧵

78,417 просмотров • 2 месяцев назад

Code Channels are now live in Slack! How to use them as a multiplayer IDE: in this demo we 1. Create a new Code Channel 2. Build a new feature 3. Invite a teammate to collaborate and review the PR 4. Receive an edited screen recording of the new feature being built and tested with Computer Use in Devin Code channels are ephemeral, so once the feature is complete we remove the channel and move on.

Code Channels are now live in Slack! How to use them as a multiplayer IDE: in this demo we 1. Create a new Code Channel 2. Build a new feature 3. Invite a teammate to collaborate and review the PR 4. Receive an edited screen recording of the new feature being built and tested with Computer Use in Devin Code channels are ephemeral, so once the feature is complete we remove the channel and move on.

50,178 просмотров • 1 месяц назад

Opus 5.5 goes absolutely insane for video production 😂

Opus 5.5 goes absolutely insane for video production 😂

29,815 просмотров • 23 дней назад

This is like having an army of white hat hackers at your disposal. They break into your app, prove the exploit works, an open a PR that fixes it. It takes about 10 seconds to set up and can be automated to run nightly or weekly for any codebase. In an eval of real and recent vulnerabilities, which the models had never seen, Security Swarm found the bug in 72% of cases, the highest recall of any tool we tested, at ~2/3 the cost of the next most accurate alternative. 🤯 If you have an OSS repo you'd like me to fork and run Security Swarm on, drop a link!

This is like having an army of white hat hackers at your disposal. They break into your app, prove the exploit works, an open a PR that fixes it. It takes about 10 seconds to set up and can be automated to run nightly or weekly for any codebase. In an eval of real and recent vulnerabilities, which the models had never seen, Security Swarm found the bug in 72% of cases, the highest recall of any tool we tested, at ~2/3 the cost of the next most accurate alternative. 🤯 If you have an OSS repo you'd like me to fork and run Security Swarm on, drop a link!

120,361 просмотров • 3 месяцев назад