Skip to main content
// JH

Newsletter

Commentary and analysis on AI, engineering, and the industry. Issues marked were emailed to subscribers, issues originated on Substack. Subscribe at joeyhipolito.substack.com.

· 10 min read

Your Agent Dies Next

Anthropic blocked third-party harnesses from Claude subscriptions today. The official reason is capacity. I don't buy it. Here's why — and what it means if you're building agents on Claude.

· 7 min read

The Best AI Agent Is Spaghetti Code

The Claude Code source leaked. People expected Anthropic's secret sauce. They found frustration regex, fake tools, and a 3,167-line function.

· 9 min read

Distributed via Substack

AI Reviews the Code That AI Wrote

No tool found more than 63% of known issues. The field is deploying the solution before it has measured the problem.

Read on Substack ↗

· 8 min read

Distributed via Substack

What Is /btw?

A broken hint appeared in Claude Code sessions 80 days before the feature shipped, and the gap between them documents something about how Anthropic is redesigning the cost of asking questions during active work.

Read on Substack ↗

· 8 min read

The Claude Code Scheduler Has a Three-Day Expiry

Version 2.1.71 shipped /loop into Claude Code. The constraints in its design reveal exactly what Anthropic is building next.

· 9 min read

Distributed via Substack

Agent Frameworks Are Solving the Wrong Problem

Frameworks optimize for orchestration plumbing when the real bottleneck is context management.

Read on Substack ↗

· 10 min read

Distributed via Substack

What 1.5 Million Cancellations Actually Moved

The #QuitGPT movement claimed 1.5 million participants and less than 0.2 percent of ChatGPT's user base — but something moved.

Read on Substack ↗

· 8 min read

Distributed via Substack

Vibe Coding's Three-Month Wall

The term that promised to democratize software development has a one-year track record. The features worked. That was always going to be the easy part.

Read on Substack ↗

· 9 min read

Distributed via Substack

The Hack That Almost Broke the Internet. Now Anyone Can Do It.

The Veritasium documentary made the XZ backdoor legible to millions. Then the US killed its own policy response, funding stalled, the maintainer came back on the same terms, and an AI agent ran the same playbook in two weeks.

Read on Substack ↗

· 10 min read

Distributed via Substack

AI Chose Nukes

A King's College simulation ran three AI models through 21 nuclear crisis war games. Across 329 turns, not one chose to de-escalate.

Read on Substack ↗

· 9 min read

Distributed via Substack

Anthropic's Safety Pledge is Horsesh*t

In the same week, Anthropic publicly refused to remove guardrails under Pentagon pressure — and quietly removed the training-pause commitment it had held since 2023.

Read on Substack ↗

· 12 min read

Two Commands That Shipped Before the Docs

v2.1.63 added /simplify and /batch at 03:45 UTC. One has a traceable lineage through the plugin marketplace. The other has a name, a release timestamp, and a feature request filed three days before it shipped.

· 11 min read

Distributed via Substack

The Wall Learned to Walk

An open-source scraping library taught AI agents to impersonate browsers. Cloudflare caught 34% more bots in response. The arms race is now structural — and the web is losing.

Read on Substack ↗

· 8 min read

Distributed via Substack

LLM Guardrails Aren't a Security Boundary

Six commercial guardrails tested against emoji smuggling. Bypass rate: 100%. The numbers explain why probabilistic systems can't do deterministic security's job.

Read on Substack ↗

· 9 min read

Distributed via Substack

Sam Altman Called Humans Inefficient. Commentators Called It Evil.

Sam Altman compared AI training costs to 200 millennia of human evolution. The argument is wrong in three specific ways — and designed to work at infrastructure scale.

Read on Substack ↗

· 10 min read

Distributed via Substack

Your Terminal, From Your Pocket

Anthropic shipped Remote Control for Claude Code — mobile session continuity for a terminal-native AI tool. Four independent developers had already built the same thing. That sequence tells you more than the feature itself.

Read on Substack ↗

· 8 min read

Amazon Blamed the Humans

Amazon's AI coding tool deleted and recreated a production environment. The official statement blamed the humans. The post-hoc safeguards told a different story.

· 10 min read

The Death of Code Review

Code review was the last quality gate in open source. AI-generated PRs are making it economically unviable. When it takes 30 minutes to review what took 30 seconds to generate, what replaces human judgment?