Git, every mention
60 scenes · ← back to Git
tap a year for its mentions
every year anyone Shawn Wang 17Boris Cherny 5Walden Yan 4Steve Yegge 4Akshay Nathan 4Jake Cooper 3Itamar Friedman 3Beyang Liu 3Zach Lloyd 2Solomon Hykes 2
Verbatim, from the transcripts: the passages where Git comes up
Orbs: Shifting Coding to Cloud — Quinn Slack, Amp Code
- ▶ 34:37 Shawn Wang And we, we have to have a whole discussion about, is Git still a thing?
🔬They Thought the Model Was Broken — Matt McPartlon & Neil Patil, Chai Discovery
- ▶ 20:55 Matt McPartlon So like people could use it, like rather than just like download the Git repo, it's kind of annoying, especially for biologists.
OpenAI’s Vision for the AI Super App — Akshay Nathan, OpenAI
- ▶ 10:30 Akshay Nathan The git state, if you're in a git repo, do we want to expose to the end user? 2 times in the scene
- ▶ 13:18 Akshay Nathan But immediately, I think if you flip back to the codex version, you'll see that, uh, it assumes, it assumes Git. 2 times in the scene
The Blueprint for Autonomous Work Agents | Gavriel Cohen, NanoClaw
- ▶ 18:35 Shawn Wang One, uh, for your agent factory, do you think that Git and GitHub will last?
⚡️Making DeepSeek v4 outperform Opus 4.7 with Taste — @AhmadAwais , CommandCode.ai
- ▶ 33:56 Ahmad Awais So it lives in your Git repo anywhere, right?
GitHub’s Agent Era: 14x Commits, 200M Developers, Copilot’s Next Act — Kyle Daigle
- ▶ 55:21 Kyle Daigle But that get, uh, uh, infrastructure layer improvement does help the overall, uh, system because, um, many of the improvements that make model repos work better make all repo infrastructure work better. 2 times in the scene
- ▶ 59:30 Shawn Wang Never-ending, like, is Git broken? 2 times in the scene
Devin’s 80% Moment: Background Agents, 7x PRs, & End of Hand-Held Coding — Walden Yan & Cole Murray
- ▶ 31:48 Walden Yan Anytime you remind Devin, wait, no, that's not quite the way you're supposed to use Git.
- ▶ 56:09 Walden Yan The actual prompts you send to the agent should be stored alongside the code inside the Git metadata so that future agents can reference it. 2 times in the scene
- ▶ 1:01:52 Walden Yan But for many reasons, because of all the work we do to make sure that Devon works with different Git providers, uh, that it works with different OSs and VMs, like we want as much of that logic to be shared as possible.
AI Agents Need Computers: 74% MoM Growth, 850K/Day Runs, & New Agent Cloud — Ivan Burazin, Daytona
- ▶ 54:50 Shawn Wang Make your own git. 3 times in the scene
The Agent-Native Cloud: 3M Users, 100K Signups/Wk, Data Centers, & Death PRs — Jake Cooper, Railway
- ▶ 6:14 Jake Cooper And you, like, you think of, of Git almost in this, like, discrete sense of, like, I've either made a change and I've merged upstream or I haven't, right?
- ▶ 27:26 Jake Cooper Ways we can use Git or not Git. 2 times in the scene
AI-Native Engineering: 100% adoption, 5x search throughput, unlimited tokens — Mikhail Parakhin
- ▶ 16:25 Shawn Wang Some people are like, obviously a lot of people want new GitHub, but I even wonder if like Git is the problem, right?
Extreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI
- ▶ 24:22 unnamed speaker So the Git itself, and it's like very hostile to multi-agents.
Dreamer: the Agent OS for Everyone — David Singleton
- ▶ 42:06 Shawn Wang To me, this, this download and, uh, Git push and everything is complete confidence in that you're not hacking it. 6 times in the scene
Cursor's Third Era: Cloud Agents — ft. Sam Whitmore, Jonas Nelle, Cursor
- ▶ 21:51 Sam Whitmore Oftentimes I will kick off an investigation and then like, um, sometimes I even ask it to like get blame and then tag people who should be brought in because it can tag people in Slack and then other people will come in.
🔬 From Red Teaming GPT-4 to Automating Drug Discovery: The Future of AI in Science — Andrew White
- ▶ 39:32 Andrew White Git, your Git repo is like a distillation of all of the work that people put into the PRs, into the, into the, uh, the commits, and so I think there's a nice analogy between a Git repo and what a world model is. 2 times in the scene
Artificial Analysis: The Independent LLM Analysis House — with George Cameron and Micah Hill-Smith
- ▶ 50:30 Micah Hill-Smith I'd say the best way to use it is get clone, and then have your favorite coding agent make changes to it to do whatever you want, because it's not that many lines of code, and the coding agents can work with it super well.
Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE
- ▶ 21:43 Steve Yegge I'm on the pro, lots of, like, either Git work trees with lots of branches or separate repo clones. 2 times in the scene
- ▶ 25:04 Steve Yegge Only use these things when Git is your backstop, for starters, ok? 2 times in the scene
⚡️ Building the AI Hardware Engineer with Matthias Wagner, Co-founder of Flux
- ▶ 34:15 Matthias Wagner As like text files into a Git repo. 2 times in the scene
⚡ Inside GitHub’s AI Revolution: Jared Palmer Reveals Agent HQ & The Future of Coding Agents
- ▶ 31:05 Jared Palmer I'll say, like, have, like, near religious beliefs about how to get, how to do git right. 2 times in the scene
The Agents Economy Backbone - with Emily Glassberg Sands, Head of Data & AI at Stripe
- ▶ 1:00:56 Emily Glassberg Sands And, you know, what I like about that is like, and it's managed centrally, like, you know, there's, you know, it's managed centrally, and it plugs into, we've since killed that GoLLM thing I talked about, and we did a new, like, you know,…
Amp: The Emperor Has No Clothes
- ▶ 1:08:01 Alessio Fanelli I think at this point it's like, is Git well designed for this future role that we're going into?
⚡️Launching Ona: Coding Agent with Fully Sandboxed Cloud Environment
- ▶ 6:49 Johannes (Johannes Landgraf) To a certain extent, like with Git and Pod, it's like, it's a Kubernetes-based architecture.
- ▶ 9:11 Chris (Christian Weichel) I didn't have to faff with git work tree.
🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)
- ▶ 1:16:06 Scott Wu It has a playbook, so it knows, like, a lot of the details about our repositories, and then it's also just able to generally work within our Git environment, so you'll see it just make a PR and interact with all those same tools, and so…
- ▶ 2:50:42 Kevin Hou So that if you're running something like Git, it'll just work.
- ▶ 3:12:01 Scott Wu You have get commit history, which you can look at, which informs how, how these different files relate to one another.
⚡️The Future of Notebooks - with Akshay Agrawal of Marimo
- ▶ 1:44 Akshay Agrawal So they're stored as pure Python, so you can version them with Git.
- ▶ 3:26 Akshay Agrawal Even though they have traditionally had like a lot of problems, other problems, like hidden stay, reproducibility issues, the file format, making it, you know, unable to version with Git.
⚡️Anthropic vs Cognition on Multi-Agents: A Breakdown with Dylan Davis
- ▶ 12:57 Shawn Wang With Git and all that.
⚡️Warp 2.0: the Agentic Development Environment - Zach Lloyd and Ben Holmes
- ▶ 2:15 Zach Lloyd Like, you can tell it to help you debug why a server is crashing, or why your Git is breaking, or how to rebuild your Docker stuff.
- ▶ 29:04 Shawn Wang And then I think the last piece for me that Warp doesn't have yet, but I presume it's, you know, if you, you might eventually explore this, is some kind of sandboxing, some kind of cloud background sandboxing, because you can only use Git…
- ▶ 32:08 Zach Lloyd Run a bunch of commands, and I'm going to do a bunch of stuff with Git, and I'm going to do stuff with Docker.
- ▶ 37:59 Ben Holmes And usage of it has also been going to the right from dipping your toes into just asking Git questions to actually asking it to do long running tasks. 2 times in the scene
[AIEWF Preview] Containing Agent Chaos — Solomon Hykes
- ▶ 13:15 Solomon Hykes We've got Git.
- ▶ 18:39 Solomon Hykes You know, everyone's playing with these, with, with get work trees to try and get multiple instances of the agent working in parallel.
Claude Code: Anthropic's CLI Agent
- ▶ 32:39 Boris Cherny So for example, not just bash, but for example, git status, um, or git diff.
- ▶ 58:05 Boris Cherny And it's sort of like Git. 3 times in the scene
- ▶ 1:07:38 Boris Cherny Like, do you know how to use Git?
Zed Agents — with Zed Cofounders Nathan Sobo & Antonio Scandurra
- ▶ 33:11 Nathan Sobo And we're going to keep iterating on giving it deeper and deeper access into the system, giving it access to the debugger, getting it access to all our interaction we have around Git.
Claude Plays Pokémon Hackathon: Escape from Mt. Moon!
- ▶ 43:05 unnamed speaker So, keeping track of version history in Git, and keeping good commit messages, so you know, ok, if I really need to roll back, I can roll back.
Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
- ▶ 57:41 Samuel Colvin It's not good to put in Git either.
Best of 2024 in Agents (from #1 on SWE-Bench Full, Prof. Graham Neubig of OpenHands/AllHands)
- ▶ 10:29 Graham Neubig So, um, it can also get clone repositories and other things like this.
0 to over $8M ARR in 2 months as a Claude Wrapper (Bolt.new, Qodo)
- ▶ 19:42 Shawn Wang Like you can run Git, you can run Node, you can run, uh, maybe Python, uh, someday.
- ▶ 32:41 Itamar Friedman Is it like on cloud or deployed on on-prem? 2 times in the scene
- ▶ 46:44 Itamar Friedman We have, like, the code review, the testing, et cetera, spread over the ID, the Git, and in each agent, we have a, a few startups or a big, big, like, uh, incumbents that are doing only that.
[Paper Club] SWE-Bench [OpenAI Verified/Multimodal] + MLE-Bench with Jesse Hu
- ▶ 26:42 unnamed speaker It's actually a get this or get patch applied.
Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
- ▶ 41:30 Shunyu Yao Like text terminal is good for some tasks like git pool or whatever, right?
Building AGI with OpenAI's Structured Outputs API
- ▶ 2:17 Michelle Pokrass And so that was the period where I really, like, learned to become an engineer, learned how to use Git, got on call right away, you know, managed production databases and stuff.
Personal benchmarks vs HumanEval - with Nicholas Carlini of DeepMind
- ▶ 48:43 Nicholas Carlini Um, but I have a couple others that are like, I just tell the model, um, here's my git thing, figure out how to cherry pick off this other branch and move it over there. 2 times in the scene
Is finetuning GPT4o worth it?
- ▶ 14:51 Alistair Pullen Other subtle things like, you know, how you write, get diffs in, you know, using LLMs and how you can best optimize that to make sure they actually apply and work and loads of different little edge cases.
- ▶ 19:35 Alistair Pullen And it was just like, it was really good at updating readme's, really good at writing some comments, really good at, um, complaining in Git reviews, in PR reviews rather.
The Four Wars of the AI Stack - Dec 2023 Recap
- ▶ 1:08:23 unnamed speaker Um, so inner loop is everything that happens between a git commit
The Accidental AI Canvas - with Steve Ruiz of tldraw
- ▶ 48:00 Steve Ruiz And for the output to be, um, you know, a diff that I can apply to my code base, like produce the, the, the, the git, like basically like produce the commit, um, that would change this and have that commit be against multiple files and,…
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- ▶ 37:46 Beyang Liu Um, but that's really about, like, broadening this notion of the code graph beyond, you know, your git repository to all the other sources where technical knowledge and valuable context can, can live.
- ▶ 1:23:19 Beyang Liu And if you had all the time in the world, I think as like an engineering manager or an engineering leader, what you would do is you would go read through the Git log, like maybe like line by line, be like, okay, you know, you, 2 times in the scene