{"id":1152,"date":"2023-03-19T20:43:16","date_gmt":"2023-03-19T19:43:16","guid":{"rendered":"https:\/\/cerovac.com\/a11y\/?p=1152"},"modified":"2023-03-20T21:01:08","modified_gmt":"2023-03-20T20:01:08","slug":"machine-learning-and-artificial-intelligence-still-cant-deliver-accessible-code-when-asked","status":"publish","type":"post","link":"https:\/\/cerovac.com\/a11y\/2023\/03\/machine-learning-and-artificial-intelligence-still-cant-deliver-accessible-code-when-asked\/","title":{"rendered":"Machine learning and artificial intelligence still can’t deliver accessible code when asked"},"content":{"rendered":"\n

With all the attention around ChatGPT (opens in new window)<\/a> I must say I wanted to check it as well. I got some code from a coworker and saw immediate problems with it. It was looking extremely good until I checked what it really does and how it works though. To make it work I needed to fix a lot of things, but at first glance it seemed correct.<\/p>\n\n\n\n

And that is the scary part. I would be really happy if it would work, don’t get me wrong. But I think that the plausible answers it offers, plausible at first glance, will potentially do more harm than good.<\/p>\n\n\n\n

It is obvious that so called large language models have a lot of potential. I will not deny this fact. I loved the more theoretical answers on accessibility it provided. But code related answers were problematic. I even tested it with simpler algorithms for sorting arrays and needed dozens of prompt improvements to get correct answer. Again – not a problem if we are aware of it. But if we aren’t aware of it’s over-confidence, then we may do a lot of harm and get even more problems.<\/p>\n\n\n\n

It’s confidence is amazing, then you check the code, line by line, run it and it wasn’t doing what you wanted. I used some hours to redefine my prompts and on the end I got a simple sorting algorithm to work. It helped me. But that was a simple and closed algorithm for sorting an array. When I tried to get an accessible widget by prompting ChatGPT I got the same confidence but quite poor or even totally wrong answers.<\/p>\n\n\n\n

As mentioned – this can be very dangerous if people can’t really know the effects of the produced code. I totally understand the reasons though.<\/p>\n\n\n\n

\n

With 98% of all websites out there having accessibility issues it’s not weird that a lot of code examples out there have the same problems. And when we use the same pool of poor examples to teach artificial intelligence it should not come as a surprise when they can’t really deliver.<\/p>\nmy reflection about the causes behind poor delivery by ChatGTP.<\/cite><\/blockquote>\n\n\n\n

I don’t have a clue about what sources did ChatGPT consume, but the reason for it’s problems with wrong answers is for sure that – poor sources. When humans will know how to write code that will make things accessible the robots will be able to learn it as well.<\/p>\n","protected":false},"excerpt":{"rendered":"

I wanted to check for myself it ChatGPT can help delivering more accessible code. And after multiple trials I gave up. The reason for it’s confident but wrong example code is clear to me and when you read this post it will also be clear to you.<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[65,10],"tags":[546,588,589,547],"class_list":["post-1152","post","type-post","status-publish","format-standard","hentry","category-future-of-a11y","category-practical-a11y","tag-artificial-intelligence","tag-chatgpt","tag-large-language-models","tag-machine-learning"],"_links":{"self":[{"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/posts\/1152","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/comments?post=1152"}],"version-history":[{"count":0,"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/posts\/1152\/revisions"}],"wp:attachment":[{"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/media?parent=1152"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/categories?post=1152"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cerovac.com\/a11y\/wp-json\/wp\/v2\/tags?post=1152"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}