{"id":90,"date":"2023-07-06T02:39:02","date_gmt":"2023-07-06T02:39:02","guid":{"rendered":"https:\/\/blog.gwadej.org\/micro-musings\/?p=90"},"modified":"2023-07-06T02:41:21","modified_gmt":"2023-07-06T02:41:21","slug":"chatbots-dont-help-programmers","status":"publish","type":"post","link":"https:\/\/blog.gwadej.org\/micro-musings\/2023\/07\/chatbots-dont-help-programmers\/","title":{"rendered":"ChatBots don&#8217;t help programmers"},"content":{"rendered":"\n<p><a rel=\"noreferrer noopener\" href=\"https:\/\/hackaday.com\/2023\/06\/08\/contrary-view-chatbots-dont-help-programmers\/\" target=\"_blank\">Chatbots don&#8217;t help programmers<\/a> summarized an <a href=\"https:\/\/cacm.acm.org\/blogs\/blog-cacm\/273577-ai-does-not-help-programmers\/fulltext\" target=\"_blank\" rel=\"noreferrer noopener\">article<\/a> from Bertrand Meyer.<\/p>\n\n\n\n<p>Meyer suggests that an AI programming assistant as \u201ca cocky graduate student, smart and widely read, also quick to apologize, but thoroughly, invariably, sloppy and unreliable\u201d.<\/p>\n\n\n\n<p>A lot of people suggest that using an AI chatbot as an assistant might not result in a correct program, but that it would give a starting point that a good programmer can fix.<\/p>\n\n\n\n<p>Most of the examples I see <em>proving<\/em> this depend on having the chatbot generate code in a language or style that the experimenter does not know. This gives an illusion that it can help generate code more quickly than the developer would have. Unfortunately, if you don&#8217;t know the language\/framework you are generating, your ability to <em>evaluate<\/em> the code suffers from the Dunnig-Kruger effect.<\/p>\n\n\n\n<p>Meyer sums up the problem here well with: <\/p>\n\n\n\n<blockquote class=\"wp-block-quote\">\n<p>What use do I have for a sloppy assistant? I can be sloppy just by myself, thanks, and an assistant who is even more sloppy than I is not welcome.&#8221;<\/p>\n<cite>Bertrand Meyer<\/cite><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Chatbots don&#8217;t help programmers summarized an article from Bertrand Meyer. Meyer suggests that an AI programming assistant as \u201ca cocky graduate student, smart and widely read, also quick to apologize, but thoroughly, invariably, sloppy and unreliable\u201d. A lot of people suggest that using an AI chatbot as an assistant might not result in a correct\u2026 <span class=\"read-more\"><a href=\"https:\/\/blog.gwadej.org\/micro-musings\/2023\/07\/chatbots-dont-help-programmers\/\">Read More &raquo;<\/a><\/span><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[33],"tags":[64,5,63],"_links":{"self":[{"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/posts\/90"}],"collection":[{"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/comments?post=90"}],"version-history":[{"count":3,"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/posts\/90\/revisions"}],"predecessor-version":[{"id":93,"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/posts\/90\/revisions\/93"}],"wp:attachment":[{"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/media?parent=90"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/categories?post=90"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.gwadej.org\/micro-musings\/wp-json\/wp\/v2\/tags?post=90"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}