<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body dir="auto"><div dir="ltr"></div><div dir="ltr">Yes, if you’re a programmer. A lot of real-world business scenarios are basically a non-technical person using English to give a (flawed, incomplete) specification, and a programmer using their expertise not only to implement but also to fill in the incomplete parts of the specification and also to determine what missing parts of the specification can’t be interpolated and have to be asked about. That sort of filling in missing parts based on precedent is the exact sort of thing these AI are good at.</div><div dir="ltr"><br></div><div dir="ltr">Jeff</div><div dir="ltr"><br><blockquote type="cite">On Mar 31, 2023, at 4:27 PM, Mig Mit <migmit@gmail.com> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr"><meta http-equiv="content-type" content="text/html; charset=utf-8">How is it going to benefit anyone though? English, like all natural languages, is terrible for describing algorithms. It is way easier to just code the damn thing.<br><br><div dir="ltr">Sent from my iPad</div><div dir="ltr"><br><blockquote type="cite">On 2023. Apr 1., at 1:24, Yasuaki Kudo <yasu@yasuaki.com> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr"><meta http-equiv="content-type" content="text/html; charset=utf-8"><div dir="ltr"></div><div dir="ltr">There is TTS (text to speech) and STT (speech to text) Former is easier, latter is harder.</div><div dir="ltr"><br></div><div dir="ltr">Similarly, is it possible that we generate a huge variations of English explanation of correct compiled programs (like TTS - easy-ish, because we can program English explanations algorithmically ) and the get GPT-like-things to learn from that huge sample so it can convert human instructions to accurate programs? (like STT - hard),</div><div dir="ltr"><br></div><div dir="ltr"><br></div><div dir="ltr"><blockquote type="cite">On Apr 1, 2023, at 08:08, Branimir Maksimovic <branimir.maksimovic@gmail.com> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr"><meta http-equiv="content-type" content="text/html; charset=utf-8">Of course it’ useless. GPT should be tested with something that can’t be found<div>on internet :P</div><div><br></div><div>I tried with problem euler 512, it can’t find optimal solution, but can perform</div><div>microoptimisations of existing solution, which is still impressive :P</div><div><br></div><div>Greets, Branimir.</div><div> </div><div><div><br><blockquote type="cite"><div>On 1. 4. 2023., at 01:01, Alexey Vagarenko <vagarenko@gmail.com> wrote:</div><br class="Apple-interchange-newline"><div><div dir="auto">Isn’t binary search useless for lists? It performs worse than full list traversal.</div><div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">Сб, 1 апр. 2023 г. в 03:43, Branimir Maksimovic <<a href="mailto:branimir.maksimovic@gmail.com">branimir.maksimovic@gmail.com</a>>:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="line-break:after-white-space">I was thoughtt from my mathematic logic proffesor in 1987 that algorithm for making algorithms<div>doesn’t exist. He proved that there is no algorihm for provin hieor order logic formulas…</div><div><br></div><div>Greets, Branmir.</div></div><div style="line-break:after-white-space"><div><br><div><div><br><blockquote type="cite"><div>On 31. 3. 2023., at 23:37, Yasuaki Kudo <<a href="mailto:yasu@yasuaki.com" target="_blank">yasu@yasuaki.com</a>> wrote:</div><br><div><div dir="auto"><div dir="ltr"></div><div dir="ltr">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?</div><div dir="ltr"><br></div><div dir="ltr">- Easy to specify the desired outcome</div><div dir="ltr">- Easy to verify results</div><div dir="ltr"><br></div><div dir="ltr">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.</div><div dir="ltr"><br></div><div dir="ltr">But GPT4 gets much closer to completion compared to GPT3.5</div><div dir="ltr"><br></div><div dir="ltr">I wonder what "GPT-native" programming language might look like😄</div><div dir="ltr"><br></div><div dir="ltr">-Yasu</div><div dir="ltr"><br></div><div dir="ltr"><br></div><div dir="ltr"><br><blockquote type="cite">On Apr 1, 2023, at 06:24, Levent Erkok <<a href="mailto:erkokl@gmail.com" target="_blank">erkokl@gmail.com</a>> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr">This code is buggy when lo + hi overflows your integer type. Classic (extremely) corner case bug: <a href="https://ai.googleblog.com/2006/06/extra-extra-read-all-about-it-nearly.html" target="_blank">https://ai.googleblog.com/2006/06/extra-extra-read-all-about-it-nearly.html</a><br><div><br><blockquote type="cite"><div>On Mar 31, 2023, at 1:02 PM, Gregory Guthrie <<a href="mailto:guthrie@miu.edu" target="_blank">guthrie@miu.edu</a>> wrote:</div><br><div><div style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none"><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif">From a colleague:<u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"> GPT Pretty smart(?!).<u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif">But this is of course simple, and searchable.<u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><u></u> <u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif">Still…<u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif">--------------------------------------------------------------------------------------------------<u></u><u></u></div><p class="MsoNormal" style="margin:0in 0in 12pt;font-size:11pt;font-family:Calibri,sans-serif">GPT-4 when prompted:<u></u><u></u></p><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><b>Write binary search in Haskel. Print results using putStrLn. Ensure bug-free code by specifying preconditions, postconditions, invariants, variants, internal states.</b><u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><u></u> <u></u></div><p class="MsoNormal" style="margin:0in 0in 12pt;font-size:11pt;font-family:Calibri,sans-serif">gives the following response:<u></u><u></u></p><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><b>-- Binary search in Haskell<br>-- Precondition: the list is sorted in ascending order<br>-- Postcondition: the function returns the index of the target element if found, or Nothing otherwise<br>-- Invariant: the search space is always within the bounds of the list<br>-- Variant: the search space decreases by half at each recursive call<br>-- Internal state: the lower and upper bounds of the search space<br><br>binarySearch :: Ord a => [a] -> a -> Maybe Int<br>binarySearch xs x = go xs x 0 (length xs - 1)<br> where<br> go xs x lo hi<br> | lo > hi = Nothing -- base case: search space is empty<br> | x == midElem = Just mid -- base case: target element is found<br> | x < midElem = go xs x lo (mid - 1) -- recursive case: search in the left half<br> | otherwise = go xs x (mid + 1) hi -- recursive case: search in the right half<br> where<br> mid = (lo + hi) `div` 2 -- calculate the middle index<br> midElem = xs !! mid -- get the middle element<br><br>-- Print results using putStrLn<br>main :: IO ()<br>main = do<br> let xs = [1, 3, 5, 7, 9] -- a sorted list of integers<br> let x = 5 -- a target element to search for<br> let result = binarySearch xs x -- call the binary search function<br> case result of -- pattern match on the result<br> Nothing -> putStrLn "Element not found" -- print a message if Nothing is returned<br> Just i -> putStrLn $ "Element found at index " ++ show i -- print a message with the index if Just i is returned</b><u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><u></u> <u></u></div><p class="MsoNormal" style="margin:0in 0in 12pt;font-size:11pt;font-family:Calibri,sans-serif">The above code runs:<u></u><u></u></p><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><b><a href="https://onecompiler.com/cpp/3z48yt2pp" style="color:rgb(5,99,193);text-decoration:underline" target="_blank">https://onecompiler.com/cpp/3z48yt2pp</a></b><u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><u></u> <u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><u></u> <u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><span id="m_-4047222526348405260cid:image001.png@01D963E1.B0EB6AB0"><image001.png></span><u></u><u></u></div><div style="margin:0in;font-size:11pt;font-family:Calibri,sans-serif"><u></u> <u></u></div></div><span style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none;float:none;display:inline!important">_______________________________________________</span><br style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none"><span style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none;float:none;display:inline!important">Haskell-Cafe mailing list</span><br style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none"><span style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none;float:none;display:inline!important">To (un)subscribe, modify options or view archives go to:</span><br style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none"><a href="http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe" style="color:rgb(5,99,193);text-decoration:underline;font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px" target="_blank">http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</a><br style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none"><span style="font-family:SFHello-Regular;font-size:14px;font-style:normal;font-variant-caps:normal;font-weight:400;letter-spacing:normal;text-align:start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none;float:none;display:inline!important">Only members subscribed via the mailman list are allowed to post.</span></div></blockquote></div><br><span>_______________________________________________</span><br><span>Haskell-Cafe mailing list</span><br><span>To (un)subscribe, modify options or view archives go to:</span><br><span><a href="http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe" target="_blank">http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</a></span><br><span>Only members subscribed via the mailman list are allowed to post.</span></div></blockquote></div>_______________________________________________<br>Haskell-Cafe mailing list<br>To (un)subscribe, modify options or view archives go to:<br><a href="http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe" target="_blank">http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</a><br>Only members subscribed via the mailman list are allowed to post.</div></blockquote></div><br></div></div></div>_______________________________________________<br>
Haskell-Cafe mailing list<br>
To (un)subscribe, modify options or view archives go to:<br>
<a href="http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe" rel="noreferrer" target="_blank">http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</a><br>
Only members subscribed via the mailman list are allowed to post.</blockquote></div></div>
_______________________________________________<br>Haskell-Cafe mailing list<br>To (un)subscribe, modify options or view archives go to:<br>http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe<br>Only members subscribed via the mailman list are allowed to post.</div></blockquote></div><br></div><span>_______________________________________________</span><br><span>Haskell-Cafe mailing list</span><br><span>To (un)subscribe, modify options or view archives go to:</span><br><span>http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</span><br><span>Only members subscribed via the mailman list are allowed to post.</span></div></blockquote><span>_______________________________________________</span><br><span>Haskell-Cafe mailing list</span><br><span>To (un)subscribe, modify options or view archives go to:</span><br><span>http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</span><br><span>Only members subscribed via the mailman list are allowed to post.</span></div></blockquote><span>_______________________________________________</span><br><span>Haskell-Cafe mailing list</span><br><span>To (un)subscribe, modify options or view archives go to:</span><br><span>http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe</span><br><span>Only members subscribed via the mailman list are allowed to post.</span></div></blockquote></body></html>