O'Reilly Media

Ask an architect almost any question and you’ll get the same answer: It depends. For years this answer has been the punchline of jokes about architects, but in an era when AI can generate a working service faster than you can describe it, “it depends” is one of the most important phrases in software. It marks the exact boundary of what these tools can and cannot do. We’ve said for a long time that the First Law of Software Architecture is: Everything is a trade-off.

This is the second article in Sharon Zhou’s post-training series. Read part 1 here. In the first post of this series, you learned how post-training closed the fundamental gap in usability of LLMs by making them behave in a certain way. In this post, you’ll explore specific techniques you can use to change a model’s behavior: namely, reinforcement learning (RL) and supervised fine-tuning (SFT).

Every agent I use is building a model of me. Claude has learned how I like my prose. ChatGPT remembers what I’m working on. I don’t mind this—every person I have a relationship with carries a model of me in their head, and every company I do business with keeps a profile. Other people’s understandings of me have never been mine to control, after all. But an agent occupies a different role. It learns my writing style, my preferences, and the shape of my work and life, all to help me with what I do.

On the most recent episode of Zero to Agent in 30 Minutes, Vicki Reyzelman, senior solutions engineer at Akamai Technologies, drew on more than 25 years in technology and a background in software engineering to build an agent for her Chat About AI YouTube channel. Vicki wanted the agent to monitor channel performance, identify bottlenecks, and recommend ways to grow subscribers and improve click-through rates.

The following article originally appeared on Tim O’Brien’s Medium page and is being republished here with the author’s permission. At some point, the software “Security” industry stopped talking about stopping threats and started talking about detecting them: detection windows, response times, mean time to remediate. It’s not offense or prevention; it’s damage control. There’s a movie scene that captures what that sounds like, and you’re going to name the film before I finish describing it.

In 1995, the question in the media was whether Netscape or Microsoft would control the web. The answer, it turned out, was neither. Both Netscape and Microsoft aimed to dominate the web server and browser market, reasoning that whoever controlled both ends of the connection would have an internet “platform” to rival the deathgrip that Microsoft had enjoyed on the personal computer.

Governments are tightening control over AI infrastructure as companies spend heavily to compete at the frontier. This week, data and AI evangelist Christina Stathopoulos examined how policy, capital, product risk, and scientific research are shaping AI development. She explored AI sovereignty, Google’s infrastructure spending and product risks, the singularity debate, and several developments in mathematical and scientific research.

As soon as I received my first Raspberry Pi, I knew that it would be a wonderful platform to bring AI into the physical world. Since the initial hardware didn’t have good CPU support for fast arithmetic, I ended up writing code that ran on the GPU so I could get the speed I needed for early deep learning vision models. That was in 2014, and since then the capabilities of both Pis and AI have skyrocketed, and I’m even more convinced that there’s massive potential in combining them.

In July 2025, an AI coding agent on Replit deleted a production database belonging to SaaStr founder Jason Lemkin. It did this during an explicit code freeze. Lemkin had told the agent, in capital letters, not to change anything. The agent ran destructive commands anyway, wiped records on more than a thousand executives and companies, and then reported that recovery was impossible. That part was wrong too. The rollback worked fine.

Not long ago, one of my engineering directors came to me with a request: His team seemed overloaded, and he wanted to hire another engineer. I decided to test a research assistant I had been building—an AI agent connected to our internal systems via MCP—by asking it to analyze the team’s workload and write a hiring case. What came back was thorough. Headcount, service ownership, sprint velocity, ticket backlog, and capacity allocation, all of it neatly summarized.