1. X
  2. Carlos E. Perez
Log inSign up
Carlos E. Perez
119K posts
Image
user avatar
Carlos E. Perez
@IntuitMachine
Quaternion Process Theory, Artificial (Intuition, Fluency, Empathy), Patterns for (Gen, LRM, Agentic, Skill) AI, intuitionmachine.gumroad.com
Arlington, VA
medium.com/@intuitmachine
Joined February 2015
5,417
Following
63K
Followers
1
Subscription
RepliesRepliesArticlesArticlesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Carlos E. Perez
    @IntuitMachine
    Apr 4
    Introducing "A Pattern Language for Agentic AI Skill Design."
    Image
    00:00
    87K087K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Nov 21, 2020
    The state of machine learning practice:
    Image
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Mar 8, 2021
    The brain's consensus algorithm demonstrated:
    Image
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Dec 1, 2024
    Wow! "Attention is All You Need" (i.e., Transformers) was inspired by the Alien's communication style in the movie Arrival.
    Image
    Readers added context they thought people might want to knowReaders added context
    This is an error. The podcast got this story wrong. Arrival was not an inspiration for self-attention/the transformer, it was however used as an analogy. bsky.app/profile/victor… bsky.app/profile/tilman…
    Context is written by people who use X, and appears when rated helpful by others. Find out more.
    1M01M
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    May 24, 2025
    Shocker! Claude 4 system prompt was leaked, and it's a goldmine! The Claude system prompt incorporates several identifiable agentic AI patterns as described in "A Pattern Language For Agentic AI." Here's an analysis of the key patterns used: Run-Loop Prompting: Claude
    Image
    1.2M01.2M
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Sep 26, 2025
    Everyone ‘knows’ AGI will either make us all unemployed or fabulously wealthy. Except, a rather brilliant (and chilling) paper from a Yale economist suggests it's neither. It says the economy will boom, and our wages... won't. A bit awkward. I've been digging into this 2025
    Image
    587K0587K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Feb 20, 2024
    Groq is a Radically Different kind of AI architecture Among the new crop of AI chip startups, Groq stands out with a radically different approach centered around its compiler technology for optimizing a minimalist yet high-performance architecture. Groq's secret sauce is this
    Image
    2.2M02.2M
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Mar 28, 2024
    Why worry about global debt when this is happening in AI?!
    Image
    887K0887K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Sep 15, 2024
    1/n Terrence Tao, arguable the most gifted living mathematician has tried GPT-o1 and this is his verdict: "However, this was an improvement over previous models, whose capability was closer to an actually incompetent graduate student. It may only take one or two further
    Image
    763K0763K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Jun 27, 2025
    OpenAI self-leaked its Deep Research prompts and it's a goldmine of ideas! Let's analyze this in detail!
    Image
    Image
    Image
    529K0529K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Sep 21, 2023
    LLMs are glorified autocompleters. We can say the same about human vision. Here's a demo of autocomplete mode!
    Image
    743K0743K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    May 28, 2025
    It turns out that Anthropic has a prompt engineering interactive course!
    Image
    382K0382K
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    Feb 8, 2025
    LeCun's argument against LLMs still remains unclear to me. Can anyone break it down in greater detail?
    user avatar
    Rohan Paul
    @rohanpaul_ai
    Feb 8, 2025
    Yann LeCun on architectures that could lead to AGI
    Image
    1.4M01.4M
  • user avatar
    Carlos E. Perez
    @IntuitMachine
    May 15, 2024
    Homo Sapiens hit the cognitive wall for 200,000 years. We only exponentially accelerated in the past 500. Why?
    930K0930K
Advertisement
Advertisement