Seonglae ChoQuick tip for human from Andrej Karpathy
- Describe the single, next concrete, incremental change
- Don’t ask for code, ask for approaches
- pick an approach, draft code
- review / learn: pull up docs, ask for explorations, …
- wind back, try different approach
- test → commit → ask for suggestion on what could be implemented next
Method
- Stuff everything relevant into context (AI Readability)
- Describe the next single, concrete incremental change we're trying to implement
- Don't ask for code, ask for a few high-level approaches, pros/cons.
- Pick one approach, ask for first draft code.
- Review / learning phase: ask for explanations, clarifications, changes, wind back
- Test
- Commit
- Ask for suggestions on what we could implement next
- Repeat
Documentation
LLMs are strong with whiteboarding but weak with improvements
- Plan.md
- Spec.md
- Feedback
Vibe Coding Techniques
Vibe Coding Platforms
Longer horizon task
- GPT-5.2: Emphasizes completeness and accuracy, may be somewhat slower
- Opus 4.5: Faster progress but may sacrifice completeness
Andrej Karpathy: Software Is Changing (Again)
Andrej Karpathy's keynote on June 17, 2025 at AI Startup School in San Francisco. Slides provided by Andrej: https://drive.google.com/file/d/1a0h1mkwfmV2PlekxDN8isMrDA5evc4wW/view?usp=sharing
Chapters:
00:00 - Intro
01:25 - Software evolution: From 1.0 to 3.0
04:40 - Programming in English: Rise of Software 3.0
06:10 - LLMs as utilities, fabs, and operating systems
11:04 - The new LLM OS and historical computing analogies
14:39 - Psychology of LLMs: People spirits and cognitive quirks
18:22 - Designing LLM apps with partial autonomy
23:40 - The importance of human-AI collaboration loops
26:00 - Lessons from Tesla Autopilot & autonomy sliders
27:52 - The Iron Man analogy: Augmentation vs. agents
29:06 - Vibe Coding: Everyone is now a programmer
33:39 - Building for agents: Future-ready digital infrastructure
38:14 - Summary: We’re in the 1960s of LLMs — time to build
Drawing on his work at Stanford, OpenAI, and Tesla, Andrej sees a shift underway. Software is changing, again. We’ve entered the era of “Software 3.0,” where natural language becomes the new programming interface and models do the rest.
He explores what this shift means for developers, users, and the design of software itself— that we're not just using new tools, but building a new kind of computer.
More content from Andrej: https://www.youtube.com/@AndrejKarpathy
Thoughts (From Andrej Karpathy!)
0:49 - Imo fair to say that software is changing quite fundamentally again. LLMs are a new kind of computer, and you program them *in English*. Hence I think they are well deserving of a major version upgrade in terms of software.
6:06 - LLMs have properties of utilities, of fabs, and of operating systems → New LLM OS, fabbed by labs, and distributed like utilities (for now). Many historical analogies apply - imo we are computing circa ~1960s.
14:39 - LLM psychology: LLMs = "people spirits", stochastic simulations of people, where the simulator is an autoregressive Transformer. Since they are trained on human data, they have a kind of emergent psychology, and are simultaneously superhuman in some ways, but also fallible in many others. Given this, how do we productively work with them hand in hand?
Switching gears to opportunities...
18:16 - LLMs are "people spirits" → can build partially autonomous products.
29:05 - LLMs are programmed in English → make software highly accessible! (yes, vibe coding)
33:36 - LLMs are new primary consumer/manipulator of digital information (adding to GUIs/humans and APIs/programs) → Build for agents!
Some of the links:
- Software 2.0 blog post from 2017 https://karpathy.medium.com/software-2-0-a64152b37c35
- How LLMs flip the script on technology diffusion https://karpathy.bearblog.dev/power-to-the-people/
- Vibe coding MenuGen (retrospective) https://karpathy.bearblog.dev/vibe-coding-menugen/
Apply to Y Combinator: https://ycombinator.com/apply
Work at a startup: https://workatastartup.com
https://www.youtube.com/watch?v=LCEmiRjPEtQ
‣
Vibe Coding Terminal Editor
I wrote a small tool for myself as my biannual routine check of where llms are currently at. I think I've learned a bunch from this exercise. This is frustrating! I don't want to learn by trial and error, I'd rather read someone's blog post with lessons learned. Sadly, most of the writing on the topic that percolates to me tends to be high-level --- easy to nod along while reading, but hard to extract actionable lessons. So this is what I want to do here, list specific tricks learned.
https://matklad.github.io/2025/08/31/vibe-coding-terminal-editor.html
Andrej Karpathy on Twitter / X
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper…— Andrej Karpathy (@karpathy) February 2, 2025
https://x.com/karpathy/status/1886192184808149383
Vibe Coding Is The Future
Andrej Karpathy recently coined the term “vibe coding” to describe how LLMs are getting so good that devs can simply “give in to the vibes, embrace exponentials, and forget that the code even exists.” We dive into this new way of programming and what it means for builders in the age of AI.
Apply to Y Combinator: https://ycombinator.com/apply
Chapters (Powered by https://bit.ly/chapterme-yc) -
0:00 Intro
0:42 What is vibe coding?
1:00 What founders in the current YC batch are saying
4:35 Debugging and building systems
6:59 The models people are using now
10:01 What percentage of code is being written by LLM’s?
11:58 What changed and what stayed the same?
18:08 How Triplebyte did candidate assessments and how would that change in this era
21:37 Key skills that will remain relevant
23:01 How do you develop taste without classical training?
30:59 Outro
https://www.youtube.com/watch?v=IACHfKmZMr8
Andrej Karpathy on Twitter / X
Noticing myself adopting a certain rhythm in AI-assisted coding (i.e. code I actually and professionally care about, contrast to vibe code).1. Stuff everything relevant into context (this can take a while in big projects. If the project is small enough just stuff everything…— Andrej Karpathy (@karpathy) April 25, 2025
https://x.com/karpathy/status/1915581920022585597
True no-code
Code Review standards should be differentiated (core code needs thorough review, vibe code only needs to pass tests)
Vibe code isn't meant to be reviewed *
How to stay in control of codebase and not lose vibe code productivity boost. Explicit vibe/human code separation through modular approach
https://monadical.com/posts/vibe-code-how-to-stay-in-control.html
Kid
Thomas Wolf on Twitter / X
we've seen nothing yet! hosted a 9-13 yo vibe-coding event w. @robertkeus this w-e (h/t @antonosika @LovableBuild)takeaway? AI is unleashing a generation of wildly creative builders beyond anything I'd have imaginedand they grow up *knowing* they can build anything! https://t.co/KoS5sCgWvH pic.twitter.com/b5fvFwkMCP— Thomas Wolf (@Thom_Wolf) May 19, 2025
https://x.com/Thom_Wolf/status/1924399746447269963
