undefined | Better HN

0 pointsBoorishBears2y ago0 comments

Consideration -> Implementation -> Verification is a super low friction way to improve how LLMs do at coding tasks (or most tasks really).

Me: We want to swap keys with values in a Ruby hash, what are some considerations?

LLM: When swapping keys with values in a Ruby hash, there are a few considerations to keep in mind. First, it's important to note that swapping keys and values can change the order of the hash, which may affect the behavior of your code. Additionally, if the hash contains duplicate keys, swapping the keys and values may not have the desired effect. It's also worth noting that swapping keys and values does not affect the hash's size or the number of keys it contains. Is there anything else you would like to know?

Me: Let's implement the swap

LLM: Sure! Here is an example of how you can swap the keys and values of a Ruby hash using the each method:

    hash = {a: 1, b: 2, c: 3}

    hash.each do |key, value|
      hash[value] = key
    end

    # Output:
    # {1: "a", 2: "b", 3: "c"}

This code iterates over the hash using the each method, and for each key-value pair, it sets the value of the key to the value of the previous key. Is there anything else you would like to know?

Me: Did we miss anything?

LLM: No, that covers the basics of swapping keys and values in a Ruby hash. Is there anything else you would like to know?

0 comments

2 comments · 1 top-level

zevyoura2y ago· 1 in thread

But this is wrong in at least two ways:

> Additionally, if the hash contains duplicate keys, swapping the keys and values may not have the desired effect.

You can't have duplicate keys in a hash.

More importantly, their implementation adds the swapped pairs but does not remove the original k/v pairs, which is both incorrect and does not match the output it prints.

BoorishBearsOP2y ago

It looks like you can have duplicate keys so I'll give it the benefit of the doubt: https://stackoverflow.com/questions/6808801/ruby-hash-with-d...

But maybe this is why they still used GPT-4 for benchmarking, GPT-4's take:

Actually, there is a mistake in that response. The code snippet I provided modifies the original hash during iteration, which can lead to unexpected results. Also, the code can't handle the case where there are duplicate values.

A safer and more accurate way would be to create a new hash and then populate it with the swapped keys and values:

   hash = {a: 1, b: 2, c: 3}
   swapped_hash = {}

   hash.each do |key, value|
      swapped_hash[value] = key
   end

    puts swapped_hash
    # Output:
    # {1 => :a, 2 => :b, 3 => :c}

In this example, we avoid modifying the original hash while iterating over it, and the potential problems that can cause. Additionally, please note that if the hash contains duplicate values, some entries might be overwritten in the new hash since hash keys must be unique.

Also, the invert method is a built-in Ruby method for swapping keys with values in a hash. It's a simpler approach:

   hash = {a: 1, b: 2, c: 3}
   swapped_hash = hash.invert
   
   puts swapped_hash
   # Output:
   # {1 => :a, 2 => :b, 3 => :c}

Remember that the invert method also doesn't handle duplicate values gracefully. If a value appears more than once, only one of those instances will appear in the inverted hash.

Since I wrote the original comment I tried this for common use cases I've established with 3.5 and 4 and it's still a joke. Overall OpenAI is clearly dominating this space in a way I think people are downplaying out of hope.

j / k navigate · click thread line to collapse