
Carlos E. Perez
@IntuitMachine
Followers
39K
Following
56K
Media
7K
Statuses
110K
Quaternion Process Theory, Artificial (Intuition, Fluency, Empathy), Patterns for (Generative, Reason, Agentic) AI, https://t.co/fhXw0zjxXp
Arlington, VA
Joined February 2015
Meta-cognitive prompt engineering is essentially cognitive architecture design through language - using prompts to restructure and enhance how AI systems think, rather than just what they think about. The key insight is that regular prompts operate at the content level ("What is
7
29
170
Read: The Gravity of Meaning: How AI Revealed the Strange Attractors That Shape Human Thought
intuitmachine.medium.com
On the Topology of Mind in the Age of Artificial Intelligence
0
1
2
The Gravity of Meaning: How AI Revealed the Strange Attractors That Shape Human Thought
intuitmachine.medium.com
On the Topology of Mind in the Age of Artificial Intelligence
0
0
2
When you express an intention to an AI, you’re not simply instructing a tool. You’re initiating a complex dynamic between three irreducible elements: your desire (cloudy, uncertain, full of possibility), the AI’s capability (vast, statistical, pattern-based), and what actually
2
3
10
I feel better now. Even the best firms can't fix them flashing bugs!
0
0
2
Read about cognitive limits:
medium.com
Languages are the most complex symbolic systems humans have ever created. Yet children acquire them effortlessly, without formal…
1
0
0
We are looking for a new grad engineer to join our engineering team. This is an unique opportunity to work on an high-visibility special projects with support from many industry leaders and CEOs. If you’re passionate about performance engineering, system reliability, and want
2
10
190
Oh wow! Slow empathic thinking is ... Zen or Jhana.
0
0
1
The debate shouldn't be about premature abstractions built around an agentic loop, but instead about how good an LLM agent can create and maintain a sophisticated, robust, and observable agent loop! It's never exclusively about excessive abstractions in this new AI world!
Grifters like this are wasting your time and their Dunning-Kruger opinions should be ignored by serious builders. You either build on a framework or live long enough to roll your own (which is fine btw). Here’s why: 1. The "LLM API in a while loop" is your underlying agentic
0
0
1
New book "Agentic Design Patterns" by Antonio Gulli from Google
7
39
319
How Predicting the Next Word Turns into Something That Feels Like Thought
1
2
11
Always curious and full of energy, Beagles turn every walk into an adventure 🐾🎉.
99
397
7K
Mindblown this morning! A diffusion model constructed through light!! Quantum computing is so yesterday!
10
23
195
Why does this feel like the end of workflow-like APIs for LLMs?
1
0
5
Property taxes have two main purposes (1) to pay for local shared infrastructure and (2) to discourage unproductive assets. I've seen how the absence of property tax leads to zero development. The purpose of subsidy or taxes is to encourage progress and not stagnation.
0
0
2
Why GPT-5 Guidelines Reduce Hallucinations A recent OpenAI paper on hallucinationy argues: Hallucinations are statistical, not mystical. The authors reduce generation to a binary “Is-It-Valid (IIV)” classifier and show a lower bound: generative error rate ≳ 2 × IIV
2
1
5
This is just creepy! My favorite AI model is Claude, and it just has the same tastes in books as I do!
1
0
6
How did the seven deadly sins: pride, greed, wrath, envy, lust, gluttony, and sloth, now become the virtues of this nation?
1
0
1
MAJOR ENDORSEMENT! Barack Obama (My friend Reggie Brown) — the best Obama impersonator in America — just endorsed my campaign for U.S. Congress. If Reggie says “Yes We Can,” you'd better believe it! 🇺🇸 Donate below to make sure we flip this critical swing district in 2026!
11
16
108
Are we driven by leadership that, in its denial of its own shadow, demands that everyone accept their lack of compassion and humility?
1
0
1
Have Americans become Martians (i.e., genuflecting to the God of War)?
1
0
1