[Haskell-cafe] GPT & Haskell

[Branimir Maksimovic]

I was thoughtt from my mathematic logic proffesor in 1987 that algorithm for making algorithms
doesn’t exist. He proved that there is no algorihm for provin hieor order logic formulas…

Greets, Branmir.

> On 31. 3. 2023., at 23:37, Yasuaki Kudo <yasu at yasuaki.com> wrote:
> 
> I am really curious - is it possible to create a programming language designed from the ground up to be used by GPT and similar tools?
> 
> - Easy to specify the desired outcome
> - Easy to verify results
> 
> I tried GPT4 to produce COQ proofs of Yoneda Lemma but it could not even complete the interfaces (without implementation) - they failed to compile, by being tripped up by implicit parameters etc.
> 
> But GPT4 gets much closer to completion compared to GPT3.5
> 
> I wonder what "GPT-native" programming language might look like😄
> 
> -Yasu
> 
> 
> 
>> On Apr 1, 2023, at 06:24, Levent Erkok <erkokl at gmail.com> wrote:
>> 
>> This code is buggy when lo + hi overflows your integer type. Classic (extremely) corner  case bug: https://ai.googleblog.com/2006/06/extra-extra-read-all-about-it-nearly.html
>> 
>>> On Mar 31, 2023, at 1:02 PM, Gregory Guthrie <guthrie at miu.edu> wrote:
>>> 
>>> From a colleague:
>>>   GPT Pretty smart(?!).
>>> But this is of course simple, and searchable.
>>>  
>>> Still…
>>> --------------------------------------------------------------------------------------------------
>>> GPT-4 when prompted:
>>> 
>>> Write binary search in Haskel. Print results using putStrLn. Ensure bug-free code by specifying preconditions, postconditions, invariants, variants, internal states.
>>>  
>>> gives the following response:
>>> 
>>> -- Binary search in Haskell
>>> -- Precondition: the list is sorted in ascending order
>>> -- Postcondition: the function returns the index of the target element if found, or Nothing otherwise
>>> -- Invariant: the search space is always within the bounds of the list
>>> -- Variant: the search space decreases by half at each recursive call
>>> -- Internal state: the lower and upper bounds of the search space
>>> 
>>> binarySearch :: Ord a => [a] -> a -> Maybe Int
>>> binarySearch xs x = go xs x 0 (length xs - 1)
>>>   where
>>>     go xs x lo hi
>>>       | lo > hi = Nothing -- base case: search space is empty
>>>       | x == midElem = Just mid -- base case: target element is found
>>>       | x < midElem = go xs x lo (mid - 1) -- recursive case: search in the left half
>>>       | otherwise = go xs x (mid + 1) hi -- recursive case: search in the right half
>>>       where
>>>         mid = (lo + hi) `div` 2 -- calculate the middle index
>>>         midElem = xs !! mid -- get the middle element
>>> 
>>> -- Print results using putStrLn
>>> main :: IO ()
>>> main = do
>>>   let xs = [1, 3, 5, 7, 9] -- a sorted list of integers
>>>   let x = 5 -- a target element to search for
>>>   let result = binarySearch xs x -- call the binary search function
>>>   case result of -- pattern match on the result
>>>     Nothing -> putStrLn "Element not found" -- print a message if Nothing is returned
>>>     Just i -> putStrLn $ "Element found at index " ++ show i -- print a message with the index if Just i is returned
>>>  
>>> The above code runs:
>>> 
>>> https://onecompiler.com/cpp/3z48yt2pp
>>>  
>>>  
>>> <image001.png>
>>>  
>>> _______________________________________________
>>> Haskell-Cafe mailing list
>>> To (un)subscribe, modify options or view archives go to:
>>> http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe
>>> Only members subscribed via the mailman list are allowed to post.
>> 
>> _______________________________________________
>> Haskell-Cafe mailing list
>> To (un)subscribe, modify options or view archives go to:
>> http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe
>> Only members subscribed via the mailman list are allowed to post.
> _______________________________________________
> Haskell-Cafe mailing list
> To (un)subscribe, modify options or view archives go to:
> http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe
> Only members subscribed via the mailman list are allowed to post.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.haskell.org/pipermail/haskell-cafe/attachments/20230331/9b65dd68/attachment.html>