AI writes a lot of software. Now, human code review is starting to disappear.

tech

AI writes a lot of software. Now, human code review is starting to disappear.

AI coding agents like Cursor are increasingly trusted to work autonomously, with a rise in AI-generated code reaching production directly.

TL;DR

AI coding agents are increasingly trusted to work without human oversight.
The share of AI-generated code changes reaching production without manual review has increased in the past six months.
This suggests developers are more comfortable letting AI handle larger parts of the software development process autonomously.
AI-generated code is surviving at higher rates, indicating increased developer reliability.

Weiter zum Originalartikel

Elon Musk reposted

X Freeze

Turns out Elon was completely right

The coding moat is disappearing in real time https://t.co/UYlfVV3UU7

Addy Osmani

Software quality now depends on the constraints you set around your agents.

When humans manually wrote most of the code we could look at the code itself for signs of quality. Is it clean? Is it thoughtful? Is it fast? Can another engineer understand it? Does it have tests?

Agents can now generate more code than people can read. When code generation scales beyond review, quality - checks for one or more of correctness, maintainability, security, performance etc - increasingly has to live somewhere else.

It moves into the harness, environment and operating system around the agent.

This can be the tests and deterministic checks that decide what the system is allowed to do (amongst others). Your constraints are what may eventually enable loops of agents to deliver production software reliably. They can include unit tests, property tests, acceptance tests, mutation testing and quality metrics.

This back-pressure lets the system resist bad work before it becomes somebody elses problem.

Set your constraints. They decide whether the code your agents generate is good enough to ship.

Elon Musk

This is exactly right. Source code is on the verge of becoming like assembly.

The next step is getting rid of “source code” entirely and just making an efficient binary directly with AI.

Addy Osmani reposted

Addy Osmani

Software quality now depends on the constraints you set around your agents.

When humans manually wrote most of the code we could look at the code itself for signs of quality. Is it clean? Is it thoughtful? Is it fast? Can another engineer understand it? Does it have tests?

It moves into the harness, environment and operating system around the agent.

This back-pressure lets the system resist bad work before it becomes somebody elses problem.

Set your constraints. They decide whether the code your agents generate is good enough to ship.

Addy Osmani

Code quality, taste and judgment matter - especially now that agents write most of the first draft.

@SonarSource helps set your quality gate: https://t.co/cXQFyUYNlh https://t.co/qe970slTu0

Addy Osmani

If you're building a software factory, code good enough to ship still needs human taste and ownership.

You'll likely need humans in the loop upfront for deciding on product intent, system design (if you care) and your quality bar.

Do review code (lights-on factory) but be intentional with where it's needed the most. I've found you want to watch out for where automated back-pressure breaks. Or where maintainability trade-offs need to be made.

Aim for quality checks to happen as early and continuously as possible. Not all of them have to, but this includes type systems, automated tests, mutation testing, security scanners and linting for architecture rules.

Number of checks != quality. You'll likely need to experiment with what checks give you the best signal to noise ratio. Be ready to tighten or relax your constraints deliberately.

You want to build your factory so some aspects of human taste get encoded in the environment, the agent gives you evidence of its work being right and where a human still "owns" what ships to production.

Addy Osmani reposted

The Pragmatic Engineer

An agent can tell you it's correct, not that it's good. @addyosmani, author & director of engineering, on finding your edge over AI coding agents:

“I always go back to: what is alpha? My definition of alpha is advantage. What is the current thing that models are not very good at doing?

For software engineers, we often say that your alpha is in taste. Are we building the right thing? Is the thing that we are building actually good? Sometimes people will say an agent can tell you if it's good. I push back on that. An agent can tell you if a thing looks correct, if it's matching a spec. It doesn't mean it can tell you what's good.

Good can mean good from a user experience perspective, could be delightful, could be something that a person will actually want to come back to. And it is still sufficiently nuanced that it's going to take time for models to catch up to a point where they can replace that fully.

We tell people that judgment, verification, all of these other aspects continue to be important. But even if you say, maybe a year or two from now, models will catch up. We still need engineers to be answerable for these systems. That doesn't happen overnight. That happens when you understand a system, people trust you and you have that expertise.”