标签：#opinion

Every AI code review metric you track measures the hour before merge, and that is precisely the hour when the least information exists. Acceptance rate, test pass rate, and review approval all describe how a patch looked in isolation, not how it behaves under real traffic. Revert rate is the only signal that arrives after the system has voted, which makes it the least gameable number in your pipeline. This article argues that you should stop celebrating AI patch acceptance and start measuring how many of those patches come back. Why the pre-merge metrics lie A green test run proves that a patch fits the expectations you encoded last quarter, not the behavior your users will hit tomorrow. Reviewers approve diffs under time pressure, and a cleanly formatted AI patch reads as competence even when its logic is wrong. The merge is where the real evaluation begins, and the revert is the only verdict that carries operational weight. Nobody plans a revert, so the metric cannot be gamed by prompt tweaks or review theater. The argument is not that pre-merge review is useless; it is that pre-merge signals saturate quickly. Once your review gate catches the obvious failures, the remaining defects are exactly the ones that look fine in review. Those defects surface as incidents, hotfixes, and reverts, which means your post-merge telemetry is the only source of new information. Treating acceptance as a quality metric is like judging a deployment by how well the rollout script ran. The artifact: a revert attribution watch The workflow below attributes every revert commit to the patch that caused it and computes a per-source revert rate. It requires only a git history, which makes it reproducible on any repository that has survived a few incidents. Run it on a local clone first, because a read-only analysis should never touch shared state. Step 1: List every revert commit in your window. git log --all --since = "90 days ago" --grep = "^Revert " --format = "%H %s" Step 2: Extract th

Battlefields in Ukraine are littered with the remnants of drones, which are now firmly established as a critical weapon of modern warfare. But behind all that wreckage, there’s a new gold mine for the defense sector. The data drones generate will far outlast the wars in which they are used to fight, increasingly becoming part…

Last Friday, thousands of developers opened their AI code editor and found out that one of the models inside it has an expiration date. OpenAI announced it is terminating its contract with Cursor, effective November 12, 2026. The trigger was not anything Cursor did. It was who bought them. SpaceX completed its $60 billion acquisition of Anysphere, the company behind Cursor, in mid-August. OpenAI's contract had a change-of-control clause, and the moment ownership changed, a short cancellation window opened. OpenAI used it, and it picked the latest date the clause allowed. If your daily workflow runs through an AI coding tool, this story is about you, not about Musk or Altman. It is the clearest proof yet that model access inside your editor is rented, never owned. I have spent the last two years building my own AI agent infrastructure, and this kind of news is exactly why I treat every tool in my stack as replaceable. Here is what actually happened, what it means for your setup, and the exit plan I would put in place this week. What actually happened, in plain numbers The headlines make this sound apocalyptic. The details are more useful. The deal: SpaceX agreed in June to buy Anysphere in an all-stock deal valued at $60 billion. It closed earlier this month. The cutoff: OpenAI is ending Cursor's access to its models effective November 12, 2026. It is also withholding its upcoming Astra model from the platform entirely. The stated reason: OpenAI says it cannot be confident SpaceX will operate within its terms of service. It pointed to a pattern: a Twitter data licensing deal worth about $2 million a year that Musk cut off in December 2022, and an acknowledgment earlier this year, reportedly under oath, that xAI had distilled OpenAI data for training. The actual impact: Cursor co-founder Michael Truell says OpenAI models account for roughly 5% of Cursor's AI traffic. Anthropic immediately said it would increase compute to keep Claude models flowing inside the editor.

“Runaway” AI, “rogue” agents, and “autonomous” actors—the current rhetoric would have you believe that AI agents are not only awake and aware, but angry at their creators. Prominent tech leaders such as Demis Hassabis, Dario Amodei, and Sam Altman push for regulation of these seemingly “superhuman” systems, while a separate faction, led by policy organizations…

A rollback plan tells you how to undo an AI change, but not what breaks first when the change stays in place. Most production incidents do not begin with a deliberate rollback; they begin with an unexpected failure mode that the author never tested. I now treat a passing fault drill as a precondition for reviewing any AI-generated server patch. The drill runs on a disposable server before a human reads a single line of the diff. Why a rollback plan is not enough A rollback plan answers a question about the past: how do we return the system to a known state? A fault drill answers a question about the future: what happens when this change meets a condition the author did not imagine? The second question decides whether you get paged at 3 a.m. A change with a perfect rollback can still fail in a way that nobody notices until the data is gone. Free model access changes the economics of this argument, because generation stops being the bottleneck and verification starts. When a draft is nearly free, the cheapest verification is the one that breaks the change on purpose. A rollback plan is documentation; a fault drill is evidence. Documentation tells you what should happen, while evidence tells you what actually happens on a real service manager. The fault drill in five steps The workflow assumes two cheap resources: a model that generates failure hypotheses from a diff, and a server that can be destroyed after the drill. MonkeyCode's free model access covers the first, and its free server option covers the second, so a drill costs almost nothing. Disclosure: This article was prepared as part of MonkeyCode's product outreach. Any ephemeral VM or container host works if you prefer a different provider. 1. Generate failure modes before you apply anything Ask the model to enumerate failure modes for the diff, and forbid it from proposing fixes, because fixes are a distraction at this stage. The prompt below is the one I use, and it produces a catalog that the drill can test.

Opinion: The Diff Is a Claim, the Probe Is the Proof A generated patch is a claim about how a system should behave, and a diff cannot verify that claim on its own. The only honest reviewer is the runtime itself, which means every AI-proposed change deserves a behavioral probe before a human spends attention on it. Free model access changes the economics of that review, because the verification loop no longer costs a developer's full attention or a paid compute budget. The practical implication is that a disposable server, such as the free server option in MonkeyCode, becomes the arbiter of whether a patch is even worth reading. Disclosure: This article was prepared as part of MonkeyCode's product outreach. Review sessions routinely burn forty minutes on a diff that a five-second HTTP probe would have rejected instantly, and that waste is now entirely avoidable. Why Line-by-Line Review Fails on AI Patches A human reviewer reads a diff as prose, searching for the author's intent, but an AI-generated patch has no reliable intent to recover. The model that wrote the change cannot explain why a specific flag was flipped, and the diff itself only records the surface edit. This is a fundamental mismatch between the review tool and the review question. The review question is not "what changed" but "does the system still behave correctly after this change." Runtime shape diffing answers the first question well, and I have argued before that shape is a useful gate, but shape alone misses semantic regressions. A service can keep the same endpoints, the same config keys, and the same file layout while silently returning wrong data. Behavioral probes close that gap because they test the contract between the service and its callers. A probe sends real requests, checks real responses, and records real state transitions, which is exactly the evidence a reviewer needs. This is why I take the position that the probe, not the diff, should be the primary review artifact. Treat Every Pa

Most agent tooling is still built around a single conversation: one agent, one task, one terminal, one stream to babysit. Fine for small tasks, bad for real engineering work. Herdr is interesting because it treats that as the default shape of the work. The simplest way to describe it is: Herdr is tmux for coding agents. More precisely, it is an agent multiplexer that runs inside your existing terminal. It gives each agent a real PTY, keeps processes alive where the work is happening, shows agent state, and exposes a CLI plus a local socket API. That distinction matters. Herdr is not another desktop agent app. It is a binary you run where the code and terminals live: a server, a Mac Mini, a VM, a dev machine under your desk. Close the laptop, detach, ssh back later, reattach, even from a phone. The work did not die because your terminal window did. The throughput problem Coding agents changed the cost of starting work. I can ask one agent to explore a bug, another to write a failing test, another to draft a migration plan. The bottleneck is supervision. The problem is that normal terminals do not understand supervision. tmux and Zellij give you persistence and panes, but they do not know whether an agent is blocked, working, done, idle, or just sitting there after printing a question three screens ago. Desktop apps often understand the agent state better, but then the workflow is stuck to the machine with the GUI. Worktree orchestrators can coordinate parallel tasks, but they usually want to own the workflow. Herdr sits in a useful middle: terminal model, plus agent awareness. The performance multiplier is not magic. It comes from four practical properties: Multiple agents run in real PTYs, each with its own shell, logs, prompts, and process state. Herdr rolls up semantic state, so you can see which agents are blocked, working, done, or idle. The server owns the panes, so sessions survive client detach, laptop sleep, and terminal death. The CLI and socket API let scr

Every morning, airline dispatchers, grid operators, and farmers around the world make decisions based on the same thing: a weather forecast. While these forecasts are something that most people glance at for two seconds, weather predictions influence major strategic decisions in many industries, with real money, livelihoods, and even actual lives at stake. Farmers use…

It still hits like a ton of bricks to see the steep decline in Stack Overflow questions. What does that mean about learning in our industry? Stack Overflow: When We Stop Asking originally handwritten and published with love on CSS-Tricks . You should really get the newsletter as well.