modelthinking

The more I think of it, especially after the passage of the One Big Beautiful Bill, it seems more clear that we could be on a path much like in the 60s and 70s. In fact, there are a lot of parallels, not a perfect match, but striking:

Fiscal Policy:

Then:

LBJ’s Great Society + Vietnam → soaring government spending and persistent deficits.

Now:

Post-COVI

• Instructions / System Prompt: An initial set of instructions that define the behavior of the model during a conversation, can/should include examples, rules ….

• User Prompt: Immediate task or question from the user.

• State / History (short-term Memory): The current conversation, including user and model responses that have led to this moment.

• Lo

Building Agents is less about the code you write or framework you use. The difference between a cheap demo and a “magical” agent is about the quality of the context you provide. Imagine an AI assistant is asked to schedule a meeting based on a simple email:

Hey, just checking if you’re around for a quick sync tomorrow.

The "Cheap Demo" Age

Here is some more context. The US had 82% cumulative broad money supply growth over the past decade. Egypt had 638% broad money supply growth during that same time period. And the Egyptian pound underperformed the dollar by approximately that ratio; a decade ago a US dollar was worth a bit under 8 Egyptian pounds, and today it’s worth a bit over 50

It’s clear to many that we’re already stepping into the age of wisdom work. Every CEO Dan Shipper points to the rise of the allocation economy, where the advent of AI means everyone will become a manager: “You won’t be judged on how much you know, but instead on how well you can allocate and manage the resources to get work done.” Being a great man

Connection: Vulnerability, impartiality, empathy, and wonder

The majority of us have been taught that connection is earned through achievement. We believe that once we become successful, smart, or generous enough, we’ll be worthy of connection.

But people don’t want you to be perfect. They want to be connected to you.

evidence suggests that piling on more data often hurts decision quality:

1. Too much choice stalls action. In the famous "jam study," shoppers presented with 24 flavors bought jam 3 percent of the time, while those offered just six flavors purchased 30 percent of the time—a 10-fold jump.


2. Information overload erodes well-being. Two-thirds of

Indeed, the two building blocks of a company are (1) decisions and (2) relationships. Emotional clarity underpins both of these. It’s why people like Altman hire me, because they see emotional clarity as “[o]ne of the most critical skills in a post-AGI world.”

It is the ability to recognize your emotions, feel them, and move forward unobstructed—the difference between being caught in the storm and becoming the sky that holds it. Surveys show that this kind of emotional intelligence is already the number-one criteria for managers when considering a team member for a promotion or salary increase.