Daily Archives: May 26, 2026
Macro Evals for Agentic Systems
When an agentic system fails, the problem is often larger than a single bad response. A handoff may happen too late, a specialist agent may miss the same signal across many runs, or a review process may trigger for the wrong class of cases. To improve the system, teams need to see recurring behavior across the whole population of traces.
This cookbook walks through a macro-eval workflow for a multi-agent system. We use a synthetic EV order workflow where specialist agents handle pricing, compliance, supply, factory routing, scheduling, and release decisions while market and operational conditions change.
The notebook uses precomputed synthetic traces and saved lower-level eval labels, so you can run the full workflow without an OpenAI API key. — Read More
Karpathy said vibe coding is obsolete. What he described instead is product management.
Last week, Andrej Karpathy stood in front of a room at Sequoia‘s AI Ascent event and told everyone that vibe coding (a term he invented and made popular) was already obsolete. The future, he said, is agentic engineering. He went on to list exactly what agentic engineering actually involves:
preserving quality
writing design specsvsupervising plans
inspecting diffs
writing tests
building evaluation loops
managing permissions
… [S]trip the engineer-specific vocabulary, and you have product management. — Read More
Technology usually creates jobs for young, skilled workers. Will AI do the same?
At any given time, technology does two things to employment: It replaces traditional jobs, and it creates new lines of work. Machines replace farmers, but enable, say, aeronautical engineers to exist. So, if tech creates new jobs, who gets them? How well do they pay? How long do new jobs remain new, before they become just another common task any worker can do?
A new study of U.S. employment led by MIT labor economist David Autor sheds light on all these matters. In the postwar U.S., as Autor and his colleagues show in granular detail, new forms of work have tended to benefit college graduates under 30 more than anyone else.
… The paper, “What Makes New Work Different from More Work?” is forthcoming in the Annual Review of Economics. — Read More
Anthropic Is Not on Your Side
The easiest mistake to make about Anthropic is to treat it as “OpenAI, but with a conscience.”
That story is emotionally satisfying but overly simplistic. OpenAI was the first-mover, ostensibly motivated by “AGI for the benefit of all humanity” which, at the time of writing, is still in their charter. On the surface, this sounds very similar to Anthropic’s morality.
After all, Sam Altman is easy to read, what you see is what you get. He wants money, power, control, and the largest possible seat at the table. There is nothing particularly mysterious about that. Throw a dart blindfolded in the Bay Area and you’re bound to hit a founder with the same goals.
Anthropic is harder to read because it speaks in a different register. They talk about safety and alignment, but they go beyond the CBRN and cybersecurity risks that OpenAI focuses on. Anthropic adds in x-risk, and lately, geopolitical dominance as its top-of-mind concerns. They don’t just want to win the AI race on business terms, they believe they have a personal mission to save humanity.
That is precisely why they deserve more scrutiny. — Read More
I Could’ve Made $27,843 Last Month. Here’s Why I Chose Not To.
Everywhere you look, the story is the same.
It’s exhausting.
And if you’re a seasoned professional—if you’ve managed multimillion-dollar clinical trials, orchestrated global supply chains, or built B2B digital strategies over decades—you don’t feel envy.
You feel something quieter.
Something older.
A practiced skepticism, worn smooth by years of watching hype cycles rise like tides… and recede like ghosts. — Read More
AI is doing something weird to Science
Picture Donald Knuth. Eighty-eight years old, the man who wrote The Art of Computer Programming by hand in TeX, which he invented himself to be able to write his own books. The father of algorithmic analysis. The most laudeated living computer scientist. A legend, and a well-known AI skeptic.
Now picture him reading a printed chat log between a fellow colleague and Claude Code. Not skimming. Reading it in detail, because there is something genuinely baffling about it.
… Most accounts that open with this scene take one of two off-ramps. The first off-ramp is the replacement narrative. The second off-ramp is the stochastic-parrot dismissal. — Read More
Pope Leo XIV’s Magnifica Humanitas on AI
Humanity, created by God in all its grandeur, is today facing a pivotal choice: either to construct a new Tower of Babel or to build the city in which God and humanity dwell together. Each generation inherits the task of shaping its own era, of guiding history to become a place where the dignity of every person is safeguarded, justice is promoted and fraternity is made possible. Yet every era also runs the risk of creating an inhumane and more unjust world. Whenever humanity is in danger of marring its true identity, we Christians lift our eyes to the Incarnate God, knowing that it is “only in the mystery of the Word made flesh that the mystery of humanity truly becomes clear.” [1] In Jesus Christ, this humanity in its grandeur becomes the Way, the Truth and the Life, opening the path for each of us to grow toward fullness. — Read More
Rick's Cafe AI 