Devin, every mention
109 scenes, the whole family · ← back to Devin
tap a year for its mentions
every year anyone Scott Wu 75Shawn Wang 49Walden Yan 25Alessio Fanelli 17Silas Alberti 8Anastasios Angelopoulos 7Matthias Wagner 5Vivek Ravisankar 4Ivan Burazin 4Samuel Colvin 3
Verbatim, from the transcripts: the passages where Devin comes up
Orbs: Shifting Coding to Cloud — Quinn Slack, Amp Code
- ▶ 2:51 Quinn Slack You know, Devon. 3 times in the scene
Exo: Harnesses should see their own code and logs — Alex Krentsel, UC Berekeley / Google Research
- ▶ 4:51 unnamed speaker So, so, uh, for, for my two companies, I have an internal bot that does work, and I have an external bot, Devin, that modifies the internal bot.
The Blueprint for Autonomous Work Agents | Gavriel Cohen, NanoClaw
- ▶ 6:18 Shawn Wang My last in AIE Europe, I talked about if I'm using Devon from LH Work, Town Assistant, even a little bit of Victor as well.
Devin’s 80% Moment: Background Agents, 7x PRs, & End of Hand-Held Coding — Walden Yan & Cole Murray
- ▶ 2:16 unnamed speaker Everyone is building their own devins. 6 times in the scene
- ▶ 7:47 unnamed speaker So literally after Devin was launched was there was OpenDevin.
- ▶ 9:30 Walden Yan Well, yeah, there's multiple layers to this in, in practice, and actually, it's funny you mentioned the infrastructure, because when we got started building Devon as well, we had to go figure out how to make the infrastructure as well,… 3 times in the scene
- ▶ 13:39 Walden Yan I think a lot of that, what you mentioned is why we actually from the start built Devon to what we called separate the brain from the machine. 3 times in the scene
- ▶ 23:22 Cole Murray Um, I think with Devin, you guys have had this for a while.
- ▶ 25:28 Walden Yan We try to take that a step further and say, oh, like, what if we actually made sure you could interact Devin with Devin directly on GitHub? 6 times in the scene
- ▶ 25:41 Walden Yan But there's actually quite a bit of tuning you have to do here, because you can imagine that actually, like, we recently have DevinReview, for example. 2 times in the scene
- ▶ 28:45 Walden Yan But we actually use Devon like a coworker in Slack, and that's how it's been built from the ground up. 3 times in the scene
- ▶ 31:30 unnamed speaker Walk us through the Devon memory journey, because I know there's been a journey. 8 times in the scene
- ▶ 38:58 unnamed speaker Well then I, I'm just, uh, throwing it open to you in terms of like, uh, I, I call this kind of like meta devin management. 6 times in the scene
- ▶ 45:05 unnamed speaker I, I feel Devin is slow sometimes because I'm like, well, yeah, this is very readable and very sensible, but also it is slower than it could be.
- ▶ 49:05 Walden Yan About like, uh, you know, maybe like a year and a half ago when we were in the early days of building Devon, um, we also didn't have AI that we just asked, like, how do you, you can just lock up a new group index. 5 times in the scene
- ▶ 59:05 unnamed speaker Well, Devin's good, very good at making mock servers.
- ▶ 1:00:17 unnamed speaker Um, and then, and Devin has, or Condition has just done it. 2 times in the scene
- ▶ 1:05:02 Walden Yan The SRE use case internally, we think about it as auto triage because we just want every message that comes in and that's an alert, that's a bug report to have Devon just start triaging it before anything else. 2 times in the scene
- ▶ 1:08:15 Walden Yan And so, you know, um, any listeners are welcome to, to come chat to us about that, whether using Devin or, you know, working with us.
AI Agents Need Computers: 74% MoM Growth, 850K/Day Runs, & New Agent Cloud — Ivan Burazin, Daytona
- ▶ 8:22 Ivan Burazin Devon was not public. 3 times in the scene
- ▶ 53:48 Ivan Burazin Like everyone was building up a competitor to Lovable or, or, um, or Devon or whatnot.
Senior Dev: This "Grill Me" Prompt Is Going Viral Among Top Engineers
- ▶ 6:40 Shawn Wang I also, uh, you know, consult for commission and Devin at
⚡️ Competing with ChatGPT and Sierra, building a $10M ARR company — Yasser Elsaid, Founder, Chatbase
- ▶ 57:22 unnamed speaker Obviously, I use Devin a lot, but
AI-Native Engineering: 100% adoption, 5x search throughput, unlimited tokens — Mikhail Parakhin
- ▶ 13:03 Shawn Wang Do you just use, like, like, let's say a Claude code to review tools, or do you have another set of review tools, like the Greptiles, the CodeRabbits, uh, Devon Reveals has a review tool.
⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic
- ▶ 14:27 Samuel Colvin We, so in Pylandsk AI, the guys are using Devon quite a lot. 3 times in the scene
Agent Inference at the "Speed of Light" — How NVIDIA moves like a $4.3 Trillion Startup
- ▶ 1:15:48 Shawn Wang So for example, one thing that clinician does is, before you kick off a search, they do like a fast context model, where you kick off eight parallel agents to search across the code base.
Why Every Agent Needs a Box — Aaron Levie, Box
- ▶ 49:33 Shawn Wang It powers a lot of depth and brain.
Dylan Patel Explains the AI War While Cooking | In-Context Cooking
- ▶ 21:25 Dylan Patel That does not mean, you know, a lot of people use Cloud Code without having Cloud commit for them, so you're, like, you're talking about, like, or, and then they use Codex, they use Cognition, they use, you know, or sorry, Devon, they use…
⚡️Context Graphs: according to the authors — Jaya Gupta, Ashu Garg, Foundation Capital
- ▶ 3:06 Jaya Gupta You know, we got Cloud Code, we got like Devin, we got all these customer support agents, Sierra, Decagon.
[State of Code Evals] After SWE-bench, Code Clash & SOTA Coding Benchmarks recap — John Yang
[State of Evals] LMArena's $1.7B Vision — Anastasios Angelopoulos, LMArena
- ▶ 22:55 Anastasios Angelopoulos And I think the code arena is a good example of an arena that would support a full featured harness like a Devin. 7 times in the scene
[State of AI Startups] Memory/Learning, RL Envs & DBT-Fivetran — Sarah Catanzaro, Amplify
- ▶ 21:29 Sarah Catanzaro If you are in enterprise that is adopting again, like a Devon or Augment or something like that, you probably also want your models to kind of like learn the, like.
One Year of MCP — with David Soria Parria and AAIF leads from OpenAI, Goose, Linux Foundation
- ▶ 47:09 Shawn Wang Tasks are really interesting, and we basically have to invent this, um, when we did this at, um, did like the Devon API, uh, at Cognition, and I think that's also like, uh, an interesting reinvention of, of like, well, everyone is going to…
⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
- ▶ 22:29 unnamed speaker I mean, Devin and Cascade, you know, and, uh, I, uh, so I have a personal side project where I want to make Devin for non-coding. 5 times in the scene
AI to AE's: Grit, Glean, and Kleiner Perkins' next Enterprise AI hit — Joubin Mirzadegan, Roadrunner
- ▶ 28:39 Shawn Wang This is why, like, I mean, I, I put it as, as part of my, like, why cognition thesis, core cognition, Devon cognition is very good at product and edge, but they didn't really have that much of a sales team.
⚡️ Building the AI Hardware Engineer with Matthias Wagner, Co-founder of Flux
- ▶ 2:42 Matthias Wagner You can fork VS Code. 2 times in the scene
- ▶ 21:02 Matthias Wagner You know, I was just, just last week, I was sitting here with Devin thinking through, or maybe we could have like a right-click context menu here, right? 2 times in the scene
- ▶ 22:59 unnamed speaker So first of all, before you, before this call, I actually didn't even know you used Devin, but yes, I also work on Devin. 10 times in the scene
- ▶ 36:50 unnamed speaker It's Devin, the original Devin. 3 times in the scene
- ▶ 46:43 Matthias Wagner So again, this is very similar to like, you know, what the workflow looks like with Devon or cursor, right?
Anthropic, Glean & OpenRouter: How AI Moats Are Built with Deedy Das of Menlo Ventures
- ▶ 11:06 Shawn Wang So Devin had, you know, like, I, I'm sure like there's like some pro user version of this, but I still haven't figured out how to use Devin properly with two slacks. 2 times in the scene
- ▶ 36:38 Alessio Fanelli Because if cloud code is like mid, they're better off promoting Devon and cognition to sell more tokens. 3 times in the scene
⚡ Inside Google Labs: Building The Gemini Coding Agent — Jed Borovik, Jules + AIE CODE Preview
- ▶ 30:57 unnamed speaker I don't know.
⚡️ The State of AI Engineer Hiring: Cheating, AI Adoption,Junior Devs — Vivek Ravisankar, HackerRank
- ▶ 16:06 Vivek Ravisankar So the way we test for the usage of agent stuff is less about, can you prompt the agent to do the work, but more in terms of, hey, I've actually generated a bunch of PRs from Devin or Cloud Code or Gemini or like Codex or whatever. 4 times in the scene
Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
- ▶ 23:29 Andy Konwinski Was really into sweep inch and mem GPT and we, and then Devon happened and I thought, wow, that's an interesting demo.
⚡️ Ship AI recap: Agents, Workflows, and Python — w/ Vercel CTO Malte Ubl
⚡️Claude Sonnet 4.5 and Anthropic's roadmap for Agents and Developers — Mike Krieger, Anthropic
- ▶ 20:36 unnamed speaker Uh, the, the, the cognition blog post was, was mostly like, oh, like, we, we wrote David, but like, because of the better planning, it's faster now, and so you have less hours of autonomy, but that's, that's good.
Context Engineering for Agents - Lance Martin, LangChain
- ▶ 40:26 Lance Martin Devin uses a fine-tuned model for doing summarization within the, within the context of coding.
The AI Agenda: GPT5 leaks and the business of AI News — Steph Palazzolo, The Information
- ▶ 39:53 Shawn Wang And I mean, similarly, I think, like, Devin is, is, uh, 2 times in the scene
⚡️Using RFT to Build Clinical Superintelligence
- ▶ 24:34 Alessio Fanelli Also one ideas that we gonna talk about in the prep is like the idea of Devon for clinical AI research, kind of like moving more towards in job assistance to like more long running experimental things.
🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)
- ▶ 52:42 Scott Wu Hey, I'm Scott from Cognition AI, and today I'm really excited to introduce you to Devin, the first AI software engineer. 12 times in the scene
- ▶ 1:12:14 Scott Wu I'm Scott from Cognition AI, and I'm gonna tell you guys a little bit about, um, you know, the, the, the early makings of Devon. 10 times in the scene
- ▶ 1:15:17 Scott Wu And so, you know, this is obviously kind of a toy use case, and it's, it's perhaps useful, but we use Devon all the time ourselves when we're building Devon, actually. 18 times in the scene
- ▶ 1:17:54 Scott Wu But, you know, why Devon in particular? 2 times in the scene
- ▶ 1:21:41 Scott Wu And so, you know, I mean, even a lot of the features in Devon are essentially looking over your own intern's shoulder. 10 times in the scene
- ▶ 1:24:51 Scott Wu And, you know, as we're using Devon more and more, I think one of the big things that we see actually is, this is kind of obvious perhaps, but Devon is not the one that decides what to do or what to build, you know, and there's this core… 5 times in the scene
- ▶ 1:28:22 Scott Wu So in our code base, for example, Devon has all the setup that it needs. 2 times in the scene
- ▶ 1:54:36 Shawn Wang Devon style. 2 times in the scene
- ▶ 1:55:25 Varun Mohan I think that if the answer is, like, fully agentic is called, like, is, is Devin, I think, like, yes, the answer is this product should become fully agentic, and limited human interaction is the goal, is 100% the goal, and I think,…
- ▶ 3:03:40 Scott Wu It probably should be like every two months or something like that with the pace of everything's done, but, but, but it's going to be fun to, to talk a little bit about, you know, what we've seen in the space and, and what we've learned… 5 times in the scene
- ▶ 3:12:41 Scott Wu So you would tag Devon in Slack and say, hey, by the way, we've got this bug. 10 times in the scene
- ▶ 3:36:49 Scott Wu And, and then similarly in terms of the products, you know, I think, windsurf is the agentic IDE and Devin is the first agent, right?
- ▶ 3:42:45 Alessio Fanelli So if I'm a Windsurf user, am I now getting access to Devon as well? 10 times in the scene
Cline: The Collaborative AI Coder
- ▶ 57:12 Shawn Wang So, the instantiations of this now, I would say, are background agents is, it would be codecs, for example, like, not spinning up, you know, one PR per minute, and, or Devin, or Cognition. 2 times in the scene
- ▶ 1:11:33 Shawn Wang Uh, and I think there's Devin, which is a real name, you know?
⚡️Anthropic vs Cognition on Multi-Agents: A Breakdown with Dylan Davis
- ▶ 19:09 Shawn Wang And I think it's very helpful for Devin to come on and say, like, we tried this guys. 2 times in the scene
- ▶ 24:02 Dylan Davis Kind of the whole like contradictory Devon thing of saying single agent actually works as you should define the problem you're trying to solve and then figure out what agent architecture is most suitable for that problem instead of just…
The AI Coding Factory
- ▶ 20:31 unnamed speaker When I'm boarded to Devon, for example, they have the fix prompt button, and then it refills it in their template, which is, like, give the agent instruction on how to debug, give agent instruction on how to do this, and they ask you to…
DeepWiki: The GitHub Encyclopedia
- ▶ 0:15 unnamed speaker And today we have Silas Alberti from Cognition, also known as Devin.
- ▶ 1:08 unnamed speaker And, uh, you know, I think a lot of people know about Cognition and Devon, and we can dive into that as well. 2 times in the scene
- ▶ 7:22 Silas Alberti So the thing that we wanted to figure out for DeepWiki, and this is also something that like we wanted for Devon, and this is what inspired this project in the first place. 2 times in the scene
- ▶ 11:59 unnamed speaker Is there an easy way, say if I'm using that replay cursor to like, or, you know, obviously Devon to use that kind of like deep link to pull in the right documentation from DeepWiki? 4 times in the scene
- ▶ 15:55 Silas Alberti I think it's part of the reason why we want to ship it fast, because we've, like, had this sitting around for a while, but, like, uh, mostly paywall behind Devon, and now it's, like, available to everyone on open source.
- ▶ 20:14 Silas Alberti If I, when I was onboarding onto Devon, you're like, yeah.
- ▶ 23:10 Silas Alberti It's, it's a huge problem that we face with Devon, actually, because, um, like, one of the things that makes Devon still very unique among, like, all the coding tools is that it's, it's like this, like, in the cloud agent that you can,… 4 times in the scene
- ▶ 29:02 unnamed speaker This, is this an area like, so Devin does not expose a model selector, right? 2 times in the scene
ChatGPT Codex: The Missing Manual
- ▶ 44:35 unnamed speaker Uh, I mean, uh, for what it's worth, I think the one shot thing is, um, a good angle that, that the other, the other people, you know, like, and this is me comparing you to, to alternatives like Devin and Factory and all the others.
Claude Code: Anthropic's CLI Agent
- ▶ 11:57 Shawn Wang There's the cursors of the world, there's, like, the devins of the world, there's aiders, and there's Cloud Code, and you, we can't try everything all at once.
Why Every Agent needs Open Source Cloud Sandboxes
- ▶ 3:17 Vasek Mlejnsky We wanted to build, like, a AI, like, DevIn, kind of, like, thing.
The #1 SWE-Bench Verified Agent
- ▶ 12:21 Shawn Wang There would be Devon. 2 times in the scene
Fullstack-Bench: The Eval for Coding Agents — with Sujay Jayakar, Chief Scientist, Convex
- ▶ 4:08 Alessio Fanelli One of the things we always highlight about Devon is, you know, you have the code, you have the environment and all of that.
Solve coding, solve AGI [Reflection.ai launch w/ CEO Misha Laskin]
- ▶ 23:06 Shawn Wang How will you, how will you, I guess, encourage people to think about comparing your products versus like a Devon, like a poolside, like a Magic?
Why is everyone cloning Deep Research?
- ▶ 36:44 Shawn Wang Devin will show you the plan while it's working the plan, and you can say, like, hey, the plan is wrong, and I can chat with it while it's still working. 2 times in the scene
- ▶ 38:01 Shawn Wang I guess Devon had to do this because some of these jobs, they take hours.
The AI Architect: Bret Taylor
- ▶ 17:40 Bret Taylor I think most people listening probably use, uh, copilots to code like Cursor or Devon or Microsoft Copilot or whatever.
Beating OpenAI and Anthropic by Looking At Data: the new #1 on SWE-Bench w/ W&B CTO Shawn Lewis
- ▶ 33:09 unnamed speaker Have you guys tried Devin? 3 times in the scene
OpenAI o1 isn’t a chat model (and that’s the point)
- ▶ 27:51 Alessio Fanelli I don't know what, for example, what, um, Devin is doing, like, as far as, uh, where you draw the line between chaining, just using a one and like the environment is kind of what matters.
2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- ▶ 18:07 Alessio Fanelli I mean, next year, the first thing I'm doing is signing up for Devin, signing up for the Pro ChatGPT.
- ▶ 54:50 Shawn Wang One example here is Devin, right? 4 times in the scene
- ▶ 1:25:35 Shawn Wang Devin, um, came out in March, and that was a very, very big launch. 4 times in the scene
Best of 2024 in Agents (from #1 on SWE-Bench Full, Prof. Graham Neubig of OpenHands/AllHands)
- ▶ 46:53 unnamed speaker Um, one thing I was like thinking about, uh, and there's this idea of, from, from Devin, your, your arch nemesis, uh, uh, of playbooks.
The State of AI Startups in 2024 [LS Live @ NeurIPS]
- ▶ 8:21 Pranav Reddy So cloud launched computer use, OpenAI launched code execution inside of Canvas yesterday, and then I think Devon just announced that they, you can all try it for 500 dollars a month, um, which is pretty remarkable.
Windsurf: The Enterprise AI IDE
- ▶ 17:27 unnamed speaker Dev-in style. 2 times in the scene
0 to over $8M ARR in 2 months as a Claude Wrapper (Bolt.new, Qodo)
- ▶ 18:36 Shawn Wang Cognition DevIn and a bunch of other sort of agent type startups, they all use Nullify to deploy because of this one feature.
The new Claude 3.5 Sonnet, Computer Use, and Building SOTA Agents — with Erik Schluntz, Anthropic
- ▶ 34:48 Shawn Wang And I also like the, the way that Devin does it, where you can sort of edit the plan as it goes along.
[Paper Club] SWE-Bench [OpenAI Verified/Multimodal] + MLE-Bench with Jesse Hu
- ▶ 8:12 Jesse Hu Because this also gets a little bit confusing with all the different splits, but, um, happy to touch upon, like, you know, what was going on with, like, Devin, or, uh, any of the other submissions.
- ▶ 11:34 Jesse Hu So if you go to the, so, so here, here's what's really important here, and we can go to the Devon, uh, in parallel with this. 2 times in the scene
Building AGI in Real Time (OpenAI Dev Day 2024)
- ▶ 40:17 Romain Huet And that's also what, like, Devon from Cognition can use in their own software engineer agents.
Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
- ▶ 36:06 Shawn Wang I would consider Devin to be the sort of biggest launch of the year as far as AI startups go, and, uh, you guys in the Princeton group worked on SWE agents alongside of SWE bench. 4 times in the scene
- ▶ 1:09:04 Shawn Wang That's a Devon playbook as well.
page 1 of 2 · 100 scenes per page · newest episode first next →