[thatscot]

When I work side-by-side with Claude to fix bugs or ask it to fix problems. It constantly makes mistakes, like the other day it got the concept of batchItemFailures on an sqs queue completely wrong.

How are people just firing them off to build stuff with any confidence?

[eisbaw]

https://ghuntley.com/stdlib/ applies to claude as well.

AI won't magically know your codebase unless it is pretty vanilla - but then you teach it. If it makes a mistake, teach it by adding a rule.

You have to confine the output space or else you quickly get whatever.

[thatscot]

It isn't about my codebase though, its a standard SQS concept.

[deanc]

One might argue it should know others codebases though. The fact it wouldn’t know function signatures for AWS SDK isn’t hugely promising and reflects my own experiences using LLMs