Welcome to Startups Weekly, a nuanced take on this week’s startup news and trends by Senior Reporter and co-host of Equity Natasha Mascarenhas. To receive this in your inbox, subscribe here.
Reporter’s Note: Before I get into this, thanks to the Startups Weekly readers who pointed out that last week’s link to my column was broken. If you want to know about the state of solo GPs, which, boy, is it hard, read my TC+ story here: Are Solo GPs screwed? Ok, now onto this week’s newsletter!
“AI whisperer” jobs are roles created for people who are smart engineers and able to manipulate ChatGPT or other generative AI tools to get what they want out of it. as Bloomberg reported earlier this week, these jobs can generate up to $335,000 in annual salary. Cha-ching.
That’s an impressive price for a job that would have made jaws drop just a year ago. It’s also a reminder that the rise of generative AI will create a new set of questions about how we ask questions. Just spending a few minutes playing on ChatGPT, I learned that you can get a diversity of AI-generated answers to questions just by changing a few selected words and requiring bullet points instead of three sentences.
Before we see a whole wave of AI rapid engineering consulting practices to hire: it’s a joke we already are — I thought it would be helpful to add some of the best advice I hear from the community on how to best interact with the AI so that it gives you the answers you want. We already know that he is imperfect, not all facts can be trusted, and sometimes he is at a loss for words. However, what can we do with what we have?
Many technicians chimed in on Twitter: You can see the full thread here – but here are the top five tips:
1. Overdescribe. As one person said, don’t be afraid to go extra when asking for artificial intelligence. There’s a difference between asking for a banana bread recipe and asking for a simple banana bread recipe that incorporates cardamom, bakes in less than an hour, and has a surprise ingredient. Or put another way, don’t just keep it high, be specific about the tone and complexity you prefer in responses. Over explaining and using adjectives was probably the most common advice I received when asking for advice on how to be a better prompter.
2. Ask for help. It’s not always easy to know how specific to be when applying for AI, so why not ask for help? an entrepreneur told me to ask ChatGPT how to request 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 you need (I wish humans were like this) and you’ll get a more personalized response as a result.
3. Give feedback. Let’s say I ask for: “a conversational yet informative three-sentence explanation of the impact of generative AI in education, incorporating at least one metaphor.” ChatGPT had a pretty good answer, but I didn’t like the answer. Tell that! Feedback is useful for training the AI on the types of responses you like and it takes a fraction of a second. This is how that process went for me:
Natasha: Give me a conversational yet informative three sentence explanation of the impact of generative AI in education, incorporating at least one metaphor.
ChatGPT: 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 amounts of data to provide a personalized path to knowledge. With the help of generative AI, education can become a more accessible and personalized journey, empowering students to reach new heights.
Natasha: I don’t like the virtual sherpa metaphor. Also, can you be more specific about what new heights students can reach?
ChatGPT: Generative AI can be thought of as a personal tutor that provides students with a personalized study plan that meets their individual needs and interests. Like an expert coach, the AI can identify students’ strengths and weaknesses and provide 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.
4. Ask for nuances. ChatGPT only answers what is asked, so why not ask for nuances? One founder said that they ask the pros and cons of every recommendation they request from ChatGPT.
5. Be a little embarrassed. Is it self-congratulatory to tell AI to talk like me, specifically pushing it to be flashy, charismatic, and informative? Maybe, but it helps. One of the biggest tricks I’ve learned is to include my Twitter account when I ask for a deep dive on a topic. ChatGPT responds better to “Arguing why cauliflower is the best vegetable in the tone of @nmasc_” than “Arguing why cauliflower is the best vegetable in the tone of Natasha Mascarenhas”. And since I know you’re curious about the former, I’ll leave you with ChatGPT’s argument for cauliflower supremacy:
Alright, buckle up, because I’m about to explain why cauliflower is THE BEST vegetable there is. First, let’s talk about versatility. This baby can be roasted, grilled, mashed, pureed, riced, and even made into chicken wings. Name another vegetable that can do all of that, I’ll wait.
And don’t 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’s high in fiber and low in calories. Plus, it’s a great source of antioxidants, which help fight disease and keep your body in top shape.
But let’s be real, the best thing about cauliflower is how delicious it is. Whether you’re enjoying it as a creamy soup, a spicy stir-fry, or a crispy pizza crust, cauliflower has a flavor and texture that’s second to none. And let’s not forget its ability to take on different flavors and spices, making it the ultimate canvas for creative cooking.
So there you have it folks. Cauliflower is the MVP of vegetables, and I defy anyone to prove me wrong.
Those are some initial tips I’m incorporating, but I’d still love to know what else I’m missing, so please do. throw your best tips in this thread. Also, thanks to Fundrise CMO Jon Carden. for headline inspiration!
In the rest of this newsletter, we’ll talk about Cerebral Valley and Substack. As always, you can follow me on Twitter either instagram to continue the conversation. And if you feel like supporting me extra, subscribe to my personal (and free!) Substack.
Heard in Cerebral Valley
I attended the Cerebral Valley AI conference on Wednesday, which brought together the top 200 minds in AI for a one-day deep dive. The event, organized by Newcomer and Volley, was immersive to say the least. I spoke to half a dozen YC founders building AI companies, bullish and surprisingly bearish venture capitalists and, briefly, Stability CEO and founder Emad Mostaque about keeping it real.
Here are some great phrases:
- “The six-month hiatus seems destructive and probably exorbitantly expensive,” Bucky Moore, a partner at Kleiner Perkins, said in response to the recent open letter.
- “Security research is one of the areas we’re best known for… I don’t necessarily think it’s synonymous with a technology company, a company that’s also thinking about how to take that research and turn it into something practical.” said Daniela Amodei, co-founder of Anthropic.
- “You’re building for GPT-4, but you want to build for GPT-10,” said Lisha Li, CEO of Rosebud AI.
- “Of course we are not in a bubble, this is bigger than 5G and autonomous clients,” Emad Mostaque, CEO and founder of Stability AI, said of the AI hype. “When founders come to me, I tell them to build good products and solve problems…most things remain superficial.”
And finally: If you’re still looking for more Stability, listen to my podcast interview with Credo AI founder Navrina Singh, who talked about responsible AI, governance, and fear as a not-so-great motivator.
Image Credits: fake images
Substack News Week
Blogging and media platform Substack opened a community fundraising round this week, seeking capital from its writers, both accredited and non-accredited readers. As of Friday morning, more than 6,000 investors have pledged around $6.9 million in funding.
We also talked about the crowdfunding campaign on our Equity podcast this week, which was spicier than I expected. To me, if Substack successfully raises money from its community after disclosing its financials, the stock crowdfunding world will gain a much-needed reputation and public perception boost.
This is what you should knowthrough my colleague alex william:
Ironically, Substack users might be giving the company’s professional money managers a break. Venture investors who once poured a mountain of capital into Substack don’t have to invest anymore, the incoming dilution is effectively zero, and the company gets more total funding to meet its long-term goals. For Substack, this is a win.
We won’t see this kind of riddle very often. Most startups can’t manage this type of crowdfunding because their customers pay them, not the other way around. By contrast, Substack users make their living partly or wholly with the company, so they are more interested in sticking around. This makes the Substack crowdfund unique.
Image Credits: AndreyPopov/Getty Images
Etcetera etcetera.
Spotted on TechCrunch
StellarFi lands $15 million to help people build credit by paying bills and rent on time
Groupon, which has lost 99.4% of its value since going public, names a new CEO… based in the Czech Republic
US investors cut valuation of Byju and Swiggy
twitter is dying
Apple acquired a startup that uses AI to compress videos
Spotted on TechCrunch+
Layoffs will continue until (investor) morale improves
Investors Unfazed by First Quarter Crypto Funding Decline
Launchpad Teardown: Northspyre’s $25 Million Series B Platform
What’s going on with the TikTok ban?
Blinded by the speed of change
Talk soon,
