{"id":624722,"date":"2023-04-02T09:49:24","date_gmt":"2023-04-02T14:49:24","guid":{"rendered":"https:\/\/news.sellorbuyhomefast.com\/index.php\/2023\/04\/02\/always-be-prompting\/"},"modified":"2023-04-02T09:49:24","modified_gmt":"2023-04-02T14:49:24","slug":"always-be-prompting","status":"publish","type":"post","link":"https:\/\/newsycanuse.com\/index.php\/2023\/04\/02\/always-be-prompting\/","title":{"rendered":"Always be prompting"},"content":{"rendered":"
\n

Welcome to Startups Weekly, a nuanced take on this week\u2019s startup news and trends by Senior Reporter and Equity co-host <\/em>Natasha Mascarenhas.<\/em><\/a> To get this in your inbox, subscribe <\/em>here<\/em><\/a>.<\/p>\n

Reporter\u2019s note: Before we get into this, thank you to the Startups Weekly readers who pointed out that last week\u2019s link to my column was broken. If you want to know about the state of solo GPs \u2014 which oh boy, is it rocky \u2014 please read my TC+ story here: <\/em>Are Solo GPs screwed? <\/em><\/a>Ok, now into this week\u2019s newsletter!\u00a0<\/em><\/p>\n

\u201cAI whisperer\u201d jobs are roles made for people who are savvy prompt engineers and able to manipulate ChatGPT or other generative AI tools to get what they want from it. As Bloomberg reported earlier this week<\/a>, these jobs can land up to $335,000 in annual salary. Cha-ching.<\/p>\n

It\u2019s an impressive price tag for a job role that would\u2019ve blown minds just one year ago. It\u2019s also a reminder that generative AI\u2019s boom will create a whole new set of questions about how we ask questions. By just spending a few minutes playing around on ChatGPT, I learned that you can elicit a diversity of AI-generated answers to questions just by changing a few select words and demanding bullet points versus three sentences.<\/p>\n

Before we see a whole wave of AI prompt engineering consultancy practices for hire \u2014 just kidding, we already are<\/a> \u2014 I figured it would be helpful to aggregate some of the top tips I\u2019m hearing from the community on how to better interact with AI to get it to give you the answers you want. We already know it\u2019s imperfect, it can\u2019t be trusted with every single fact, and it sometimes is left speechless. What can we do with what we\u2019ve got, though?<\/p>\n

Many techies weighed in on Twitter \u2014 you can see the full thread here<\/a> \u2014 but here are the top five tips:<\/p>\n

1. Overdescribe. <\/strong>As one person put it, don\u2019t be afraid to be extra when prompting artificial intelligence. There\u2019s a difference between asking for a banana bread recipe and asking for a simple banana bread recipe that incorporates cardamom, takes less than one hour to bake and has a surprise ingredient. Or put differently, don\u2019t just keep it high level, get specific about the tone and complexity you prefer in answers. Over explanation and adjective use was probably the most common tip I received when asking for advice on how to be a better prompter.<\/p>\n

2. Ask for help. <\/strong>It\u2019s not always easy to know how specific to get when you\u2019re prompting the AI \u2014 so why not ask for help? One entrepreneur<\/a> told me to ask ChatGPT how to prompt it based on what I want, so ask something like, what information do you need from me to create an itinerary for a San Francisco hiking trip? The AI will tell you what it needs \u2014 I wish humans were like this \u2014 and as a result, you\u2019ll get a more tailored answer.<\/p>\n

3. Give feedback. <\/strong>Let\u2019s say I ask for: \u201ca chatty but informative three-sentence explanation about the impact of generative AI on education, incorporating at least one metaphor.\u201d ChatGPT had a pretty good response, but I didn\u2019t love the response. Tell it that! Feedback is helpful to train the AI on the types of answers you like and takes a split second. Here\u2019s how that process went for me:<\/p>\n

\n

Natasha: <\/strong>Give me a chatty but informative three-sentence explanation about the impact of generative AI on education, incorporating at least one metaphor.<\/p>\n

ChatGPT:<\/strong> Generative AI has the potential to transform education by serving as a virtual Sherpa, leading students on personalized learning expeditions. Just as a Sherpa uses experience to guide climbers through treacherous terrain, AI can harness vast data to provide a customized path to knowledge. With the help of generative AI, education can become a more accessible and tailored journey, empowering students to reach new heights.<\/p>\n

Natasha: <\/strong>I don\u2019t like the virtual sherpa metaphor. Also, can you be more specific on which new heights students can reach?<\/p>\n

ChatGPT<\/strong>: Generative AI can be thought of as a personal tutor, providing students with a tailor-made curriculum that meets their individual needs and interests. Like a skilled coach, AI can identify students\u2019 strengths and weaknesses, and provide them with targeted guidance to help them excel. With the help of generative AI, students can reach new heights by unlocking their full potential and gaining a deeper understanding of complex topics.<\/p>\n<\/blockquote>\n

4. Ask for nuance. <\/strong>ChatGPT only answers what it is asked, so why not ask for nuance? A founder said that they ask for pros and cons on every recommendation that they prompt ChatGPT to give.<\/p>\n

5. Be a little cringe. <\/strong>Is it self-indulgent to tell AI to speak like me, specifically nudging it to be voicey, charismatic and informative? Maybe, but it helps. One of the biggest hacks I\u2019ve learned is to throw my Twitter handle in when asking for a deep dive on a topic. ChatGPT responds better to \u201cMake an argument for why Cauliflower is the best vegetable in the tone of @nmasc_\u201d than \u201cMake an argument for why Cauliflower is the best vegetable in the tone of Natasha Mascarenhas.\u201d And because I know you\u2019re curious about the former, I\u2019ll leave you with ChatGPT\u2019s argument on cauliflower supremacy:<\/p>\n

\n

Alright, buckle up folks, because I\u2019m about to make a case for why cauliflower is THE BEST vegetable out there. First of all, let\u2019s talk versatility. This baby can be roasted, grilled, mashed, pureed, riced, and even turned into buffalo wings. Name one other vegetable that can do all that, I\u2019ll wait.<\/p>\n

And don\u2019t even get me started on the health benefits. Cauliflower is packed with vitamins and minerals like vitamin C, vitamin K, and potassium, not to mention it\u2019s high in fiber and low in calories. Plus, it\u2019s a great source of antioxidants, which help fight off disease and keep your body in tip-top shape.<\/p>\n

But let\u2019s be real, the best thing about cauliflower is how dang delicious it is. Whether you\u2019re enjoying it as a creamy soup, a spicy stir-fry, or a crispy pizza crust, cauliflower has a flavor and texture that can\u2019t be beat. And let\u2019s not forget about its ability to take on different flavors and spices, making it the ultimate canvas for creative cooking.<\/p>\n

So, there you have it folks. Cauliflower is the MVP of vegetables, and I challenge anyone to prove me wrong.<\/p>\n<\/blockquote>\n

Those are some starter tips I\u2019m incorporating but I\u2019d still love to know what else I\u2019m missing so please do throw your top tips in this thread.<\/a> Also, shout out to Fundrise CMO Jon Carden for the headline inspiration!<\/a><\/p>\n

In the rest of this newsletter we\u2019re talking about Cerebral Valley and Substack. As always, you can follow me on Twitter<\/a> or Instagram<\/a> to continue the conversation. And if you feel like supporting me extra, subscribe to my personal (and free!) Substack.<\/a><\/p>\n

Overheard in Cerebral Valley<\/h2>\n

I attended the Cerebral Valley AI conference on Wednesday, which brought together the top 200 minds in artificial intelligence for a one day deep dive. The event, put on by Newcomer and Volley, was immersive to say the least. I spoke to half a dozen YC founders who are building AI companies, bullish and surprisingly bearish VCs, and, briefly, Stability CEO and founder Emad Mostaque, about keeping it real.<\/p>\n

Here are some great one liners:<\/h3>\n