Comment by aprilthird2021
21 hours ago
> with the right guideance, testing, framework
But you didn't write or read any of the tests so how do you know they are accurate?
21 hours ago
> with the right guideance, testing, framework
But you didn't write or read any of the tests so how do you know they are accurate?
You don’t, that’s why in agentic world your codebase is only as good as what you can prove. For this reason, you’re going to see more languages evolving feature like capability permission, effect/coeffect types, refinement types, formal verifiers, strict type checkers, static analysis and so forth. Tests are only a small part of the verification. These ideas are old and have sat outside of the mainstream coding world, but the value proposition in the ai age has changed enough their relevance is renewed.
Not arguing for not reading test code. A lot can be achieved by instructing agents to balance out the testing pyramid with the right amount of fast end to end tests, property based tests for the right things, parametrized example based tests. Ensuring the local and CI has the right mix of tests running at right time. On projects where I have less time to review AI generated code I channel my anxiety into setting up guardrails and processes for the agents and then force them to bump up against them. In the end I view it as creating frameworks which allow me to outsource some of my attention to the agents, so that I can claw back some of that time to go set up more guardrails for more agents who are working on something else.