AI

AI | Data & Analysis | Machine Learning | Tech

AI-generated code velocity mismatch creating high blast radius production incidents, and why review burden should increase not decrease with AI assistance
ByGlen Rhodes March 10, 2026

The Blast Radius Problem Nobody Wants to Talk About Amazon is holding mandatory internal meetings about AI-generated code causing production incidents. The briefing note, surfaced publicly this week, describes a pattern of incidents with “high blast radius” caused by “Gen-AI assisted changes” and includes this sentence: “best practices and safeguards are not yet established.” That…

Read More AI-generated code velocity mismatch creating high blast radius production incidents, and why review burden should increase not decrease with AI assistance
AI | Data & Analysis | Machine Learning | Tech

Anthropic releases 33-page Claude Skills playbook, positioning Claude as a composable AI operating system with repeatable workflow encoding
ByGlen Rhodes March 10, 2026

Anthropic Just Told Us What Claude Is Actually For Most people read the release of a 33-page technical playbook and think “documentation update.” I read it and thought: this is a positioning move. Anthropic just told us, in explicit terms, how they want engineers to think about Claude going forward. Not as a chat interface….

Read More Anthropic releases 33-page Claude Skills playbook, positioning Claude as a composable AI operating system with repeatable workflow encoding
AI | Data & Analysis | Machine Learning | Tech

Model routing as a deliberate engineering habit: matching task type to model capability instead of defaulting to one model for everything
ByGlen Rhodes March 10, 2026

Model Routing Is an Engineering Decision, Not an Afterthought Most engineers pick a model the way they pick a code editor. Once. Then they stop thinking about it. Maybe they upgrade when a new version drops, but the mental model stays the same: one tool, all tasks, forever. I’ve been doing this differently for about…

Read More Model routing as a deliberate engineering habit: matching task type to model capability instead of defaulting to one model for everything
AI | Data & Analysis | Machine Learning | Tech

Hot take: automated ML experiment loops change the skill profile of researchers, not the need for them, and the real risk is engineers who never learned what questions to ask
ByGlen Rhodes March 9, 2026

The Part of ML Research Nobody Talks About Most of the commentary around Andrej Karpathy’s new autoresearch repo is missing the point entirely. The repo, roughly 630 lines of code on a single GPU, runs LLM training in an autonomous loop. The agent picks architectures, tunes hyperparameters, commits code, and iterates again without a human…

Read More Hot take: automated ML experiment loops change the skill profile of researchers, not the need for them, and the real risk is engineers who never learned what questions to ask
AI | Data & Analysis | Machine Learning | Tech

Karpathy’s autoresearch repo: autonomous ML experiment loop compresses the gap between research question and validated result
ByGlen Rhodes March 9, 2026

Karpathy Just Automated the Research Grind Andrej Karpathy dropped a repo this weekend that I keep coming back to. Not because it’s flashy, not because the demo video went viral, but because it quietly describes a different way of doing ML work. The project is called autoresearch, and it is exactly what it sounds like:…

Read More Karpathy’s autoresearch repo: autonomous ML experiment loop compresses the gap between research question and validated result
AI | Data & Analysis | Machine Learning | Tech

Prediction: termination logic is the underrated design problem in agentic AI systems, not model quality or prompt design
ByGlen Rhodes March 8, 2026

The Hardest AI Problem Isn’t the Model. It’s Knowing When to Stop. Most teams building agentic AI systems are focused on the wrong problem. They spend weeks on prompt engineering. They benchmark models. They agonize over latency. And then they ship an agent that loops forever, or halts too early, or confidently hands back a…

Read More Prediction: termination logic is the underrated design problem in agentic AI systems, not model quality or prompt design
AI | Data & Analysis | Machine Learning | Tech

Claude Code /loop feature enables 3-day autonomous task scheduling, shifting AI coding tools from synchronous query tools to asynchronous agents
ByGlen Rhodes March 8, 2026

Claude Code Just Changed What an AI Coding Tool Actually Is Anthropic shipped a feature called /loop for Claude Code this week, and most of the coverage I’ve seen treats it like a quality-of-life improvement. It isn’t. It’s a category shift dressed up as a feature release. Here’s what it does: you schedule a recurring…

Read More Claude Code /loop feature enables 3-day autonomous task scheduling, shifting AI coding tools from synchronous query tools to asynchronous agents
AI | Data & Analysis | Machine Learning | Tech

Designing codebases for AI memory loss: why information architecture beats prompting every time
ByGlen Rhodes March 8, 2026

Designing Codebases for AI Memory Loss Every AI coding session starts with amnesia. The model doesn’t know your team’s conventions. It doesn’t know why you wrapped that third-party client in an abstraction layer, or why the auth module is structured the way it is, or what you decided six months ago after three hours of…

Read More Designing codebases for AI memory loss: why information architecture beats prompting every time
AI | Data & Analysis | Machine Learning | Tech

LLMs write plausible code not correct code, and what that distinction means for engineers in production
ByGlen Rhodes March 7, 2026

Plausible Is Not Correct, and That Gap Is Where Production Dies There is a framing going around right now that I think every engineer working with AI-generated code needs to internalize before they ship another feature. It comes from a post by @KatanaLarp, and the core argument is this: LLMs do not write correct code….

Read More LLMs write plausible code not correct code, and what that distinction means for engineers in production
AI | Data & Analysis | Machine Learning | Tech

OpenAI Codex Security agent and why the vulnerability validation layer is what actually matters, not the detection
ByGlen Rhodes March 7, 2026

OpenAI Just Launched a Security Agent. Here’s Why the Validation Step Is the Whole Point. Security reviews are where engineering velocity goes to die. They’re slow, they happen too late, and the person responsible for them is also the person trying to close four other tickets before end of week. Most teams treat security as…

Read More OpenAI Codex Security agent and why the vulnerability validation layer is what actually matters, not the detection