Always be prompt |


Welcome to Startups Weekly, a nuanced look at this week’s startup news and trends by Senior Reporter and Equity co-host Natasha Mascarenhas. Subscribe to receive it in your inbox here.

Reporter’s Note: Before we get into this, thanks to the Startups Weekly readers who pointed out that the link to my column from last week was broken. If you want to know more about the state of solo GPs – which one oh boy, is it rocky – read my TC+ story here: Are solo GPs screwed? Ok, now in this week’s newsletter!

“AI whisperer” jobs are roles made for people who are savvy fast engineers and are able to manipulate ChatGPT or other generative AI tools to get what they want out of it. Like Bloomberg reported earlier this week, these jobs can add up to $335,000 in annual salary. Cha Ching.

It’s an impressive price tag for a job that would have blown my mind a year ago. It’s also a reminder that the rise of generative AI will create a whole new set of questions about how we ask questions. Playing around on ChatGPT for a few minutes, I learned that you can get a variety of AI-generated answers to questions by changing just a few selected words and requiring bullet points instead of three sentences.

Before we see a whole wave of prompt engineering AI consulting firms available for hire – just kidding, we already are — I thought it would be helpful to put together some of the best tips I’m hearing from the community on how to get better at AI to make sure it gives you the answers you want. We already know it is imperfect, it cannot be trusted with every single fact, and it is speechless at times. However, what can we do with what we have?

Many techies weighed in on Twitter – you can see the full thread here — but here are the top five tips:

1. Overdescribe. As one person put it, don’t be afraid to be extra when artificial intelligence is asked. There’s a difference between asking for a banana bread recipe and asking for a simple banana bread recipe that contains cardamom, takes less than an hour to bake, and has a surprising ingredient. In other words, don’t just keep it on a high note, but be specific about the tone and complexity you prefer in answers. Over-explaining and using adjectives was probably the most common tip I got when asking for advice on being a better prompter.

2. Ask for help. It’s not always easy to know how specific to be when asking the AI ​​- so why not ask for help? An entrepreneur told me to ask ChatGPT how to ask based on what I want, so ask something like: what information do you need from me to create an itinerary for a San Francisco walking tour? The AI ​​will tell you what it needs – I wish humans were like that – and you’ll get a more tailored response as a result.

3. Give feedback. Let’s say I’m asking for: “a talkative yet informative three-sentence explanation of the impact of generative AI on education, incorporating at least one metaphor.” ChatGPT had a pretty good response, but I didn’t like the response. Tell it that! Feedback is useful for training the AI ​​in the types of responses you like and takes a fraction of a second. Here’s how that process went for me:

Natasha: Give me a talkative yet informative three-sentence explanation of the impact of generative AI on education, using 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 like a Sherpa uses his experience to guide climbers through treacherous terrain, AI can use massive amounts of data to provide a tailored path to knowledge. Using generative AI, education can become a more accessible and customized 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 tailored curriculum that meets their individual needs and interests. Like a skilled coach, AI can identify students’ strengths and weaknesses and provide them with targeted guidance to help them excel. Using generative AI, students can reach new heights by unlocking their full potential and gaining a deeper understanding of complex topics.

4. Ask for nuance. ChatGPT only answers what is asked, so why not ask for nuance? One founder said they ask for pros and cons with every recommendation they ask ChatGPT to give.

5. Be a little cringe. Is it self-indulgent to tell AI to speak like me, and specifically urge it to be voiced, charismatic, and informative? Maybe, but it helps. One of the biggest hacks I’ve learned is to throw in my Twitter handle whenever I ask for an in-depth dive on a topic. ChatGPT responds better to “Give an argument why cauliflower is the best vegetable in the tone of @nmasc_” than “Give an argument 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 over cauliflower supremacy:

All right, buckle up folks, because I’m about to defend why cauliflower is THE BEST vegetable out there. First of all, let’s talk about versatility. This baby can be roasted, grilled, mashed, mashed, riced and even turned into buffalo wings. Name another vegetable that can do all that, I’ll wait.

And I’m not even talking about 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 face it, the best thing about cauliflower is how damn delicious it is. Whether enjoyed as a creamy soup, a spicy stir-fry or a crispy pizza crust, cauliflower has a taste and texture that cannot be matched. 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.

These are some starter tips I’m including but I’d still like to know what else I’m missing so please do throw your best tips in this thread. Also shout out to Fundrise CMO Jon Carden for the headline inspiration!

In the rest of this newsletter, we’ll talk about Cerebral Valley and Substack. As always you can follow me Twitter or Instagram to continue the conversation. And if you feel like supporting me extra, sign up 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 artificial intelligence for a one-day deep dive. Hosted by Newcomer and Volley, the event was riveting to say the least. I spoke to half a dozen YC founders building AI companies, bullish and surprisingly bearish VCs, and, in short, Stability CEO and founder Emad Mostaque, about keeping it real.

Here are some great one liners:

  • “The six-month break seems destructive and probably exorbitantly expensive to consider,” said Kleiner Perkins partner Bucky Moore in response to the recent open letter.
  • “Security research is one of the areas we’re best known for…I don’t necessarily think that’s not synonymous with a tech company, a company that’s also thinking about how they can turn that research into something that’s practical,” said Daniela Amodei, co-founder of Anthropic.
  • “You build 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 self-driving customers,” Emad Mostaque, CEO and founder of Stability AI, said of the AI ​​hype. “When founders come to me, I say, build good products and solve problems… most things are still superficial.”

And finally: If you’re still looking for more stability, check out my podcast interview with Credo AI founder Navrina Singh, who talked about responsible AI, governance, and fear as a not-so-great motivator.

Robot with shopping cart.

Image Credits: Getty Images

Substack’s 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 approximately $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 announcing its financials, the equity crowdfunding world will gain much-needed reputation and public perception.

Here’s what you need to knowthrough my colleague Alex Wilhelm:

Ironically, the users of Substack might give professional money managers in the business a little breather. The venture investors who once poured a mountain of capital into Substack no longer need to invest, the inward dilution is effectively zero, and the company gets more total funding to pursue its long-term goals. For Substack, this is a win.

We don’t see these kinds of riddles very often. Most startups wouldn’t be able to handle this kind of crowdfunding because their customers pay them, not the other way around. Substack users, on the other hand, earn part or all of their life from the company, so they continue to invest more in it. This makes the Substack crowdfund unique.

Image Credits: Andrei Popov/Getty Images

etc. etc.

Seen on

StellarFi raises $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 lower the valuation of Byju and Swiggy

Twitter is dying

Apple has acquired a startup that uses AI to compress videos

Seen on

The layoffs will continue until (investor) morale improves

Investors were unimpressed by the drop in crypto finance in the first quarter

Pitch Deck Teardown: Northspyre’s $25 Million Series B Deck

What’s going on with the TikTok ban?

Blinded by the speed of change

talk soon,