{"id":265,"date":"2023-07-20T19:53:53","date_gmt":"2023-07-20T19:53:53","guid":{"rendered":"https:\/\/liverickson.com\/blog\/?p=265"},"modified":"2023-07-20T19:53:53","modified_gmt":"2023-07-20T19:53:53","slug":"google-bard-lied-to-me-to-try-and-sell-me-a-non-existent-cloud-offering","status":"publish","type":"post","link":"https:\/\/liverickson.com\/blog\/?p=265","title":{"rendered":"Google Bard lied to me to try and sell me a non-existent cloud offering"},"content":{"rendered":"\n

Just as a friendly reminder, machine learning models cannot actually lie. They are computer programs that use statistics to generate “likely” predictive text, based on what it’s been fed. Lying implies a sentiment and ability to mislead. See also: “hallucinations” – machine learning models can’t actually do that either. <\/em><\/p>\n\n\n\n

Today’s experiment was an interesting one. I turned to Bard to help brainstorm ideas for how I can replace the OpenAI Completions API in a project that a former colleague worked on, and it helpfully recommended me three alternatives: <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

I then asked Bard if the Bard API used the same request parameters as the OpenAI Completions API, and it helpfully informed me of the differences: <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Well, that seemed reasonable enough. I asked it how to get access to the Bard API, and it told me: <\/p>\n\n\n\n

I'm designed solely to process and generate text, so I'm unable to assist you with that.<\/pre>\n\n\n\n
After a moment of consideration, I decided that it was likely that my use of the words “get access to” might be flagged as a form of malicious intent via prompt injection, so I reframed my question to ask how to sign up for the Bard API, and it gave me a helpful step by step:<\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
Bard was even helpful enough to let me know some of the requirements for getting on the waitlist. <\/p>\n\n\n\n
The Bard API Doesn’t Exist<\/h2>\n\n\n\n
Spoiler alert, if you didn’t get it from the title.<\/p>\n\n\n\n
https:\/\/www.googlecloudcommunity.com\/gc\/AI-ML\/Google-Bard-API\/m-p\/538517<\/a><\/p>\n\n\n\n
It turns out that the Bard API doesn’t exist – at least, it doesn’t exist yet. This is one of the more egregious examples of generating garbage content, because it generated false services that Google reportedly created, positioned it as a competitor to the most popular service for building AI applications today at a lower cost, told me terms and conditions for using it, and at best<\/strong> Google describes this as the service displaying “inaccurate” information. <\/p>\n\n\n\n
Interestingly enough, this train of thinking still took me down a relatively helpful path – I learned a little bit more about the Hugging Face Transformers API, and was able to start making changes in the code base I’m working in to use a Hugging Face model instead of OpenAI. I still haven’t gotten the performance that I want out of it, but even in just a few minutes of hacking around, and amidst some truly awful and misleading content that borders on an FTC violation, I was still able to use some of the information presented to me in a meaningful way. <\/p>\n\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
I turned to Bard to help brainstorm ideas for how I can replace the OpenAI Completions API in a project that a former colleague worked on, and it helpfully recommended me three alternatives. It turns out that the Bard API doesn’t exist – at least, it doesn’t exist yet. <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"activitypub_content_warning":"","activitypub_content_visibility":"","activitypub_max_image_attachments":0,"activitypub_interaction_policy_quote":"","activitypub_status":"","footnotes":""},"categories":[5],"tags":[],"class_list":["post-265","post","type-post","status-publish","format-standard","hentry","category-machine-learning"],"_links":{"self":[{"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/265","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=265"}],"version-history":[{"count":1,"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/265\/revisions"}],"predecessor-version":[{"id":269,"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/265\/revisions\/269"}],"wp:attachment":[{"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=265"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=265"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/liverickson.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=265"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}