←back to thread

323 points steerlabs | 2 comments | | HN request time: 0s | source
Show context
nickdothutton ◴[] No.46192002[source]
- Claude, please optimise the project for performance.

o Claude goes away for 15 minutes, doesn't profile anything, many code changes.

o Announces project now performs much better, saving 70% CPU.

- Claude, test the performance.

o Performance is 1% _slower_ than previous.

- Claude, can I have a refund for the $15 you just wasted?

o [Claude waffles], "no".

replies(7): >>46192071 #>>46192493 #>>46192534 #>>46192607 #>>46193483 #>>46194123 #>>46194739 #
jama211 ◴[] No.46192607[source]
While you’re making unstructured requests and expecting results, why don’t you ask your barista to make you a “better coffee” with no instructions. Then, when they make a coffee with their own brand of creativity, complain that it tastes worse and you want your money back.
replies(5): >>46192820 #>>46192865 #>>46193079 #>>46195156 #>>46197842 #
1. wongarsu ◴[] No.46192865[source]
Both "better coffee" and "faster code" are measurable targets. Somewhat vaguely defined, but nobody is stopping the Barista or Claude from asking clarifying questions.

If I gave a human this task I would expect them to transform the vague goal into measurable metrics, confirm that the metrics match customer (==my) expectations then measure their improvements on these metrics.

This kind of stuff is a major topic for MBAs, but it's really not beyond what you could expect from a programmer or a barista. If I ask you for a better coffee, what you deliver should be better on some metric you can name, otherwise it's simply not better. Bonus points if it's better in a way I care about

replies(1): >>46213751 #
2. jama211 ◴[] No.46213751[source]
Sure, and LLM’s are pretty good at using measurable targets such as using tests to verify their work - if you direct them to do so.