@0xMorlex: Andrej Karpathy explained the 5 shifts that turned LLMs from chatbots into agentic systems: 00:00 - Memory turns chat i…
Summary
Andrej Karpathy outlines five key shifts—memory, multimodality, reasoning, search, and tools—that transform LLMs from simple chatbots into full agentic systems, providing a 40-minute roadmap for next-generation AI workflows.
View Cached Full Text
Cached at: 07/09/26, 11:42 AM
Andrej Karpathy explained the 5 shifts that turned LLMs from chatbots into agentic systems:
00:00 - Memory turns chat into personal AI 6:41- Multimodal AI can read the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers
This is not another video about “prompt engineering.”
It is a 40-minute roadmap for the next AI workflow: memory / vision / reasoning / search / tools.
Watch today, then read the article below on how to turn LLMs into self-improving agent loops.
Similar Articles
@0xMortyx: Andrej Karpathy in 1 hour reveal how he actually works with AI: "i just tell the machine what i want, in plain words" n…
Andrej Karpathy shares his straightforward approach to working with AI, emphasizing plain language over complex prompt engineering, and predicts that by 2026 engineers who dismiss LLMs will lose to juniors who use them effectively.
@bibryam: How I use LLMs as a staff engineer in 2026 https://seangoedecke.com/how-i-use-llms-in-2026… The biggest AI workflow cha…
A staff engineer describes how LLM agents have evolved by 2026 to become reliable collaborators for coding, debugging, and codebase research, while humans retain responsibility for judgment and review.
Chat-first AI tools break down the moment you want agents working without you
The author argues that chat-first AI tools are insufficient for building autonomous agent workflows and describes alternative primitives like scheduled triggers and sub-agent delegation, advocating for a paradigm shift from 'chat with tools' to 'autonomous processes that use LLMs'.
Andrej Karpathy: From Vibe Coding to Agentic Engineering
Andrej Karpathy discusses the December 2024 shift where LLMs reached new reliability, coining 'vibe coding' for floor-raising and 'agentic engineering' for ceiling-raising, and argues that verifiability is key to AI's jagged capabilities.
@DeRonin_: This 2-hour Andrej Karpathy lecture will teach you more about using LLMs than most AI twitter will ever figure out.. no…
Andrej Karpathy's lecture reveals an 'LLM Wiki' pattern to transform past content into a self-updating knowledge base, helping creators discover patterns in their writing.