Carlos E. Perez (IntuitMachine)
@ceperez.bsky.social
Author: Artificial Intuition, Fluency & Empathy, DL Playbook, Patterns for Generative AI, Patterns for Agentic AI
https://twitter.com/IntuitMachine
https://intuitionmachine.gumroad.com
https://medium.com/intuitionmachine
https://twitter.com/IntuitMachine
https://intuitionmachine.gumroad.com
https://medium.com/intuitionmachine
August 14, 2025 at 8:32 PM
Some new context-engineering jargon
CLEAR framework — a composition guide for writing prompts: be Concise, Logical, Explicit, Adaptive, and Reflective.
Graph-of-Thoughts (GoT) — organize thoughts as a graph (nodes = thoughts, edges = dependencies) to improve quality and cost.
CLEAR framework — a composition guide for writing prompts: be Concise, Logical, Explicit, Adaptive, and Reflective.
Graph-of-Thoughts (GoT) — organize thoughts as a graph (nodes = thoughts, edges = dependencies) to improve quality and cost.
August 13, 2025 at 6:58 AM
Some new context-engineering jargon
CLEAR framework — a composition guide for writing prompts: be Concise, Logical, Explicit, Adaptive, and Reflective.
Graph-of-Thoughts (GoT) — organize thoughts as a graph (nodes = thoughts, edges = dependencies) to improve quality and cost.
CLEAR framework — a composition guide for writing prompts: be Concise, Logical, Explicit, Adaptive, and Reflective.
Graph-of-Thoughts (GoT) — organize thoughts as a graph (nodes = thoughts, edges = dependencies) to improve quality and cost.
A year ahead of the curve. A previous book was "Artificial Intuition." I guess back then it was "Have you considered monetizing intuition?"
August 7, 2025 at 11:24 PM
A year ahead of the curve. A previous book was "Artificial Intuition." I guess back then it was "Have you considered monetizing intuition?"
The limitations of current AI
May 25, 2025 at 10:24 AM
The limitations of current AI
10 Novel Insights about Undecideability
intuitmachine.medium.com/10-novel-ins...
intuitmachine.medium.com/10-novel-ins...
May 10, 2025 at 11:52 AM
10 Novel Insights about Undecideability
intuitmachine.medium.com/10-novel-ins...
intuitmachine.medium.com/10-novel-ins...
May 3, 2025 at 1:30 PM
Quaternion Process Theory of Cognition
April 27, 2025 at 3:16 PM
Quaternion Process Theory of Cognition
The disconnect of American views about the Chinese system. @swardley.bsky.social
April 23, 2025 at 10:45 PM
The disconnect of American views about the Chinese system. @swardley.bsky.social
With my previous books—A Pattern Language for Generative AI and A Pattern Language for Long Reasoning AI—I explored how large language models can act as dynamic conversationalists and deep thinkers.
This book, A Pattern Language for Agentic AI, is a bold step into a new domain.
This book, A Pattern Language for Agentic AI, is a bold step into a new domain.
April 19, 2025 at 1:51 PM
With my previous books—A Pattern Language for Generative AI and A Pattern Language for Long Reasoning AI—I explored how large language models can act as dynamic conversationalists and deep thinkers.
This book, A Pattern Language for Agentic AI, is a bold step into a new domain.
This book, A Pattern Language for Agentic AI, is a bold step into a new domain.
Finally completed my Pattern Language AI Trilogy
April 17, 2025 at 11:23 PM
Finally completed my Pattern Language AI Trilogy
Announcement! AI Whisperer's Workshop. April 28-30th. intuitionmachine.gumroad.com/l/whispererw...
April 15, 2025 at 1:47 PM
Announcement! AI Whisperer's Workshop. April 28-30th. intuitionmachine.gumroad.com/l/whispererw...
Prompting patterns in GPT-4.1
April 15, 2025 at 10:35 AM
Prompting patterns in GPT-4.1
Claude 3.7 is still better than Gemini 2.5 in coding. Convince me otherwise.
April 8, 2025 at 4:06 PM
Claude 3.7 is still better than Gemini 2.5 in coding. Convince me otherwise.
Knowing which LLM to use for which use-case will be very important going forward because their capabilities are simply divergent in ways that are not captured by the benchmarks. Don't trust the benchmarks, don't trust the social media vibes, do your own due diligence!
April 4, 2025 at 11:03 AM
Knowing which LLM to use for which use-case will be very important going forward because their capabilities are simply divergent in ways that are not captured by the benchmarks. Don't trust the benchmarks, don't trust the social media vibes, do your own due diligence!
Vibes about vibe coding. Make sure you got an AI architect in your team!
April 4, 2025 at 10:50 AM
Vibes about vibe coding. Make sure you got an AI architect in your team!
GPT-4o is pretty decent in conjuring up recipes and visuals!
March 30, 2025 at 12:56 AM
GPT-4o is pretty decent in conjuring up recipes and visuals!
Do people recall the lies that led to the invasion of Iraq?
March 29, 2025 at 9:50 PM
Do people recall the lies that led to the invasion of Iraq?
Do people recall how the USA got into invading Iraq?
March 29, 2025 at 9:47 PM
Do people recall how the USA got into invading Iraq?
Check out the new GPT-4o generator
March 25, 2025 at 11:57 PM
Check out the new GPT-4o generator
Hey pro, upgrade your metaphors.
March 25, 2025 at 10:11 PM
Hey pro, upgrade your metaphors.
Bro.. stochastic parroting for the win!
March 25, 2025 at 9:24 PM
Bro.. stochastic parroting for the win!
Bro.. clean up your mess!
March 25, 2025 at 9:11 PM
Bro.. clean up your mess!
5 minutes later...
March 25, 2025 at 6:54 PM
5 minutes later...