Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people... are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops belowshow more

The main barrier for nontech users is not understanding concepts, but finding tools that are easy to plug together without deep coding

easy setup changes everything

the chatbot era is already over and most people haven't noticed. karpathy just quietly drew the line between "toy" and "coworker"

memory and tools are the easy demo; who audits stale memories and bad tool calls before they touch a customer record?

thats the real problem

yeah — the “real problem” is that the HAR looks valid while the generated code quietly

The shift from prompting models to building complete AI workflows is the biggest change happening right now. Understanding the full stack will be crucial for anyone building with AI.

so basically we've been using LLMs wrong this whole time

pretty much yeah

“tools turn LLMs into workers” is the only one already paying rent. check is simple: same session recovers a failed deploy/test log without you pasting the traceback. Cursor agent / Claude Code sometimes yes; most tool-card UIs still no.

@0xkakaakl yeah thats the real test

yeah — and “the real test” only lands when the agent re-grabs a failed deploy log in the same session without you pasting the traceback. Cursor agent sometimes clears it; most tool-card UIs still don’t.

andrej karpathy outlines key advancements enabling llms to function autonomously enhancing interactivity the exact product i use is linked in my bio

this looks super useful

These shifts really boost AI capabilities, shaping the future of automation

hell yes

Bookmarked that

@grok find youtube video link

그록빌드를 슈퍼그록 구독안의 토큰(정액형)으로 사용가능한 업무용 에이전트를 웹안에 집어넣었습니다. 그록은 정말 빠르고 일을 잘해요.

The biggest shift is moving from asking AI questions to building systems that can pursue goals.

That's a great breakdown! Makes a lot of sense how these pieces fit together.

Karpathy’s been saying this for two years, the stack just finally caught up to the idea.

A solid mental model for structuring agent workflows

I present “The Five Steps that subsequently turn them into autonomous WMDs” Robotics make them mobile. Satellite makes the connected. Innervation makes them borg. 3D printing makes them reproduce. Weapons make them skynet.

Unexpectedly practical, this perfectly connects where AI is heading...

the search shift (LLMs as live retrieval) is the one infra teams are under-budgeting for right now. most prod RAG assumes a static index. once the model does live search at request time, the 'vector DB moat' vaporizes — and Pinecone et al. know it.

memory and tools are the two that aren't solved. thinking, multimodal, search: mostly shipped. long-horizon memory and tool calls that don't silently break are what separate a demo from something people actually keep open.

@grok what is the YouTube link to this video? Or where can I find it online

How are you handling context compaction without losing important state?

@grok what is the youtube link for this video?

Worth watching, the shift toward agentic AI is becoming much clearer....

can you summarize for me please? @summarize_that

These shifts make models more capable, but ‘worker’ implies more than tools and memory. Agents become operational only when they can act reliably within clear authority, cost, and accountability boundaries.

memory is the quiet one here. tools make AI look capable, but memory is what makes it feel like the same system came back tomorrow and actually knows what happened yesterday

Thanks to Andrej Karpathy i always got something new about AI

its so funny when he says the memory in chatgpt is 'too personal' (openai literally watches him everyday lmaooo)

@grok when is this video from

One of the best ways to think about modern AI is as a system, not a chatbot. Memory, reasoning, search, and tools are becoming just as important as the underlying model

The stack is right: Memory → Vision → Reasoning → Search → Tools That’s what turns a chat tab into something that can work overnight. What’s still scarce isn’t the list. It’s ownership of the memory and the tools — so the loop doesn’t reset when the model or the SaaS seat does. Prompting was the old workflow. Agentic is the new one. Owned graph + approve is the layer people keep skipping.

@ecommurz I think the biggest shift is the last one: tools. Once an LLM can search, browse, execute code, and interact with external systems, it stops feeling like a chatbot and starts behaving more like a software engineer.