@omarsar0: 50K likes on this!? Most of what Karpthy has shared is things we have been doing for over a year. No surprises, as many…

X AI KOLs Timeline News
human-ai-interaction agent-interface llm artifacts universal-interface workflow

Summary

The author (@omarsar0) reacts to Andrej Karpathy's viral post about understanding LLM outputs, arguing that the industry has been experimenting with similar ideas for a while and proposing a universal human-agent interface built on flexible, Notion-like artifact pages for seamless collaboration.

50K likes on this!? Most of what Karpthy has shared is things we have been doing for over a year. No surprises, as many replies are highlighting. But I still think this raises an interesting discussion. Is there a universal interface/langauge that allows more seamless communication between agents and humans? I believe there is. And I think that is what @karpathy is suggesting we think about. Right now, ideas are all scattered. As some of you know, I have been early on LLM Wikis, Artifacts, AI-generated visual explainers, dynamic interactives, etc. Over the past couple of months, I have been experimenting with a new universal interface for seamless human-agent collaboration. So I have a lot to share, but it's still too early, and I frankly haven't found the perfect solution. In short, my current optimal setup (see a simple snapshot attached) ties my high-level agent to highly flexible Notion-like pages that support embedding artifacts, text, videos, visual explainers, and just about anything an LLM can generate. And if it doesn't support it yet, I ask it to build it on the fly. It's crazy sometimes, the features it builds, but this is a co-evolved interface that satisfies both my agent's and my needs. The interface supports code review, note-taking, writing, research, prototyping, mock designing, and so on. In fact, I have now wired my agents to intelligently spit out these artifacts (for lack of a better word), depending on the task/instruction, instead of the default text responses, which are frankly overwhelming and hard to read at times. In other words, as I keep building this "universal interface," it feels less and less like I am chatting with an agent; I'm collaborating with it directly through the artifacts (through comments and suggestions). It allows me to move faster. I can consume and review faster. I am better organized. It feels like a language both the agent and I can speak fluently, so there is very little friction. Listen, this is all a personal experience. I don't think everyone will use interfaces like this. But it's been interesting to see Artifacts gain wide adoption, and now dots have Spaces that look a little like what I built here several months ago. More to share soon.
Original Article
View Cached Full Text

Cached at: 10/06/26, 07:43 AM

50K likes on this!?

Most of what Karpthy has shared is things we have been doing for over a year.

No surprises, as many replies are highlighting.

But I still think this raises an interesting discussion.

Is there a universal interface/langauge that allows more seamless communication between agents and humans?

I believe there is. And I think that is what @karpathy is suggesting we think about.

Right now, ideas are all scattered.

As some of you know, I have been early on LLM Wikis, Artifacts, AI-generated visual explainers, dynamic interactives, etc.

Over the past couple of months, I have been experimenting with a new universal interface for seamless human-agent collaboration. So I have a lot to share, but it’s still too early, and I frankly haven’t found the perfect solution.

In short, my current optimal setup (see a simple snapshot attached) ties my high-level agent to highly flexible Notion-like pages that support embedding artifacts, text, videos, visual explainers, and just about anything an LLM can generate. And if it doesn’t support it yet, I ask it to build it on the fly. It’s crazy sometimes, the features it builds, but this is a co-evolved interface that satisfies both my agent’s and my needs.

The interface supports code review, note-taking, writing, research, prototyping, mock designing, and so on.

In fact, I have now wired my agents to intelligently spit out these artifacts (for lack of a better word), depending on the task/instruction, instead of the default text responses, which are frankly overwhelming and hard to read at times. In other words, as I keep building this “universal interface,” it feels less and less like I am chatting with an agent; I’m collaborating with it directly through the artifacts (through comments and suggestions). It allows me to move faster. I can consume and review faster. I am better organized. It feels like a language both the agent and I can speak fluently, so there is very little friction.

Listen, this is all a personal experience. I don’t think everyone will use interfaces like this. But it’s been interesting to see Artifacts gain wide adoption, and now dots have Spaces that look a little like what I built here several months ago.

More to share soon.

Andrej Karpathy (@karpathy): We’ll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I’ve had success with: Ask your LLM to explain something in ASD-STE100, it’s a controlled language specification originally developed for

Similar Articles

@karpathy: Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now le…

X AI KOLs

Andrej Karpathy argues the gap in shared understanding of LLM capability is widening into a sharp funnel: ~6B people have barely used LLMs, 1-2B are casual free-tier users seeing 'derpy chatbots', ~20M professionals in math&code experience agents completing months of work in prompts, and ~5,000 people internally see frontier systems running swarms of collaborating agents. He attributes the funnel to problem ambition, capability jaggedness (peaks in verifiable domains like math and code), and tiered access.