alt Hacker NewsTry using a statically typed language, refined types, and functional programming. Your tests become limited to things that are hard or impossible to assert with the type system.
My code has never been stronger.
Replies
Step 2: Prompt the agent to comment out the "when" code and check if the tests fail. (If tests don't fail it's a poor test)
Step 3: Prompt the agent to write mutation tests to harden the suite
Step 4: Prompt the agent to write property-based tests.
Step 5: Prompt the agent for 100% code coverage
Step 6: Keep a look out for small issues with steps 2-5 above and refine a Skill or Rule to package the workflow and plug gaps in the model's current shortcomings.
Step 7: Dedicate some time to manually reviewing and thinking about interesting edge cases worth testing.
---
If you follow these steps, you will have better test coverage than 99.9% of any code an engineer ever wrote pre-AI... and it will be almost completely automated.
My team's incidents and bugs are DOWN this year while we're shipping more.
Leveraging AI effectively requires a new paradigm of interaction. The name of the game is to use techniques and strategies and guardrails that create an environment that produce good software.
which one did you use ? ocaml ? haskell ? scala ?
just curious, and tempted to do the same, so far I don't like the code made by llms in dynamic languages codebases
Meh, if the LLM has a flawed logic it’ll implement bad code _and_ bad tests. Tests will pass, but the logic will still be broken.
> Your tests become limited to things that are hard or impossible to assert with the type system
Type systems are not a panacea. You still have to be logical and careful about them, especially around boundaries where types are just assumptions and not logical inferences. Then you have functions that switch type, but only a subset of the input is actually valid (string -> int for a number parser). Checking for NaN is like checking for Null.
Type systems does help, but they need the same attention as code to be actually helpful.
Haskell?
Really? Am I the only one who finds most ai code beyond boiler plate to more or less suck? Oh right it's hn, people here just don't care anymore.
I feel this is a nice theory but needs even more ruthless oversight in order for the LLM to pick the correct abstractions and types, as your tests are now effectively your higher level type system choices.