o3 is out and it is absolutely amazing!!

i've been playing with it for a week or so and it's already my go-to model. it's fast, agentic, extremely smart, and has great vibes.

some of my top use cases:

- it flagged every single time I sidestepped conflict in my meeting transcripts
- it spun up a bite‑size ML course that it pings me about every morning
- it found a stroller brand from one blurry photo
- it coded a new custom AI benchmark in record time
- X‑rayed an Annie Dillard classic and found writing tricks I’d never noticed before
- it even analyzed @every’s org chart to tell me what we’ll be good at shipping, and what our weaknesses are

my full review is on @every now! full review: every.to/chain-of-thoug…

ChatGPT just got an INSANE new memory update.

It remembers things about you between chats, in a sophisticated and intelligent way. Best prompt to try?

“Tell me some unexpected things you remember about me”

x.com/danshipper/sta… x.com/danshipper/sta…

Now that computers can do squishy, intuitive thinking we’re moving beyond our obsession with rationalism.

It’s why everyone in AI talks about vibes and big model smell—we need something else to describe the level of complexity computers can handle now. The predominant metaphor for business and technology in the 2010s was science. That’s why we used words like hypothesis, theory, and feedback loops.

Now that we’re using words like vibes, the metaphor is shifting to art.

HOLY SHIT they built it I wrote about this as an idea in December. Can't believe it happened so soon!

David Perell (@david_perell) is one of the best known internet writers of his generation.

@ChatGPTapp has become a go-to tool in his arsenal for creating great work. I dove deep with him on how he uses ChatGPT for:

- Doing deep reading of old books
- Finding anecdotes that spread
- Better understanding his taste
- Finding his heroes
- Understanding his blind spots as a leader
- Unpacking the strategy of his business

It was one of the deepest and most inspiring episodes we’ve ever done. And it's the first one we've ever recorded in person!

Watch below.

-----

Timestamps:
Intro 00:53
Finding and understanding his heroes 13:42
Understanding his personality and leadership style 19:14
Who does David work well with? 25:53
Workshopping The New York Times’s business strategy 36:52
Why ChatGPT is incredible at diversity, accessibility, and speed 52:54
Bringing old books like Moby Dick to life with DALLE 58:50
Using ChatGPT for deep textual analysis 1:06:29
ChatGPT for writing anecdotes that spread 1:21:04
Conversations with ChatGPT as food and drink for the soul 1:25:55 @david_perell @ChatGPTapp Watch on YouTube:

I run a media company, and I love writing. So it’s bittersweet to write this, but here it is:

AI is going to fundamentally change media in all sorts of ways over the next five years... Specifically, I think it will:

- Automate commodity content (like summaries)
- Unbundle research from narrative
- Write previously unwritten stories

Let me explain..

Let's see if GPT-4 can build ChatGPT in 10 prompts or less: Note: I'm going to do this live, I have no idea if this is going to work. Wish me luck 🫡

How to use GPT-4 to create incredible writing: AI-assisted writing gets a bad rap. People think it's bland and only able to churn out generic SEO-farm content.

But with the release of GPT-4 you can actually use AI as a serious creative partner.

Here's how:

How to turn any book into a chatbot using GPT-3: GPT-3 makes it easy to turn any piece of text into a chatbot. It's an incredible technology.

Here's one I made out of the Huberman Lab podcast transcripts:

https://twitter.com/danshipper/status/1602126357953142784

So…..I built an AI chatbot that interprets and visualizes dreams.

It uses GPT-3 and DALL-E…and the results are pretty awesome: Here’s some more spooky imagery from dreams I’ve sent it:

I loaded journal entries from the past 10 years into GPT-3 and then started asking it questions:

- What do I need to learn?
- What do I not realize about myself?
- What's obvious to everyone around me, but not to me?
- What are my deepest hopes?

The results are...pretty wild. It's very good at synthesizing and summarizing things you've written in the past, so you can see patterns.

Sometimes it repeats itself, or says things that are overly nice and rose-y...but sometimes it's really insightful.

Journaling with GPT-3 is like journaling on steroids.

Here's how: Journaling is already an effective personal development practice. It helps you:

• Get thoughts out of your head
• Show you patterns in your thinking
• Record your journey through life
• Guide your focus intentionally

But it also has problems...

How GPT-3 will turn all of your notes into an *actual* second brain: 1. Notes will be automatically tagged and linked, no manual work required.

2. Notes will be automatically enriched and synthesized to help you find patterns.

3. CoPilot-like functionality will resurface key information from previous notes in-context as you type.

I spent Christmas programming with ChatGPT.

Some observations: It’s incredibly good at helping you get started in a new project. It takes all of the research and thinking and looking things up and eliminates it…

In 5 minutes you can have the stub of something working that previously would’ve taken a few hours to get up and running.

I made a chatbot based on @hubermanlab!

Ask it any question and it will scan through Huberman Lab podcast transcripts and return the answer using GPT-3.

(You can even ask it if Cell Press journal is high quality or not....😉) @hubermanlab I love listening to @hubermanlab podcasts, but I also find that I often have a specific question related to something that he's already covered.

It's a pain to go back and try to find the answer by scrubbing through old episodes.

I think a chatbot is a really great solution.

If you want a glimpse of what you’ll be doing with generative AI in 10 years, you’ll find a lot of it on @thesephist’s laptop… He’s an AI researcher who sat with @every to show us his suite of custom-built AI tools that help him learn faster and be more productive.

Here are a few of the tools he’s built:

Every first-time entrepreneur tries a book, restaurant, or movie recommendation service as a project.

It never works...

But I have a feeling that generative AI might might turn a perennial bad idea into something that might actually work. Consider:

Every time someone recommends a book, show, movie, etc. you can text it to the model. The model might ask you questions like, "Who recommended it?", and it might search the internet to enrich its knowledge of whatever it's storing

If you asked me to pick one thing that seems to separate people who will eventually make it as creators, it’s people who have a high motor Some people just have a lot of energy to make a lot of stuff over a long period of time, and it shows in their learning rate and their number s

Interesting frames to play with in daily life:

- I am in control / not in control
- This is my fault / this is not my fault
- This is permanent / this will pass
- This is mine / this is not mine
- This has meaning / this is noise You can apply these frames to any situation happy / sad / fearful etc.

None of these frames are 100% right…but they can all be helpful or unhelpful

Why patterns in interpersonal relationships are so hard to change (and how to change them): When you identify a habitual pattern of behavior that you’d like to change, your immediate reaction is usually to feel a sense of shame or guilt for bringing something bad to a relationship with someone important (a co-founder, colleague, partner).

I accidentally fell down a rabbit hole of LessWrong consciousness explorers who seem like they’ve been thinking about similar stuff for years This is weird because I generally categorize myself as skeptical of rationalist viewpoints