howtotalktoAI
@HowToTalkToAI
Learning to talk to AI requires deep curiosity and metacognition. This podcast will talk to people who talk to AI, and see what we can learn from each other.
You might like
"Deep Inside a Real Big Empty" A Holographic Interface for Exploring Rich Multidimensional Information hypernovel.substack.com/p/deep-inside-…
After a few conversations about how nobody is going to use Tim Berners-Lee's proposed model for people managing their own social media data, etc., I figured out some ways to make it cool, with no intention of building them myself hypernovel.substack.com/p/whats-me-is-…
Its illuminating to watch open AI try to finesse it's compute load in real time. Dall-e in ChatGPT used to produce four images à la midjourney, but they regulated it to one image per query. Right now the app is overly eager to switch me into 3.5, which I'm sure is much cheaper 🤷🏼♂️
AGI's hold my beer moment: ChatGPT now remembers all your chats, knows you from them, and is agentic for $20/mo
ChatGPT already thinks it's an agent. Shouldn't be long, now. Doesn't work just yet, though. 🤣
This chat is pure gold. Happy Birthday to me!
Here's my conversation with @leecronin, a chemist and co-author of a controversial new Nature paper on the origin and evolution of life and complexity. First 3 hours are here on X. 3 hours is the current upload limit. The rest is up on YouTube, Spotify, and everywhere else.…
Every once in a while, it occurs to me that other people probably *aren't* talking to ChatGPT about the internal vector knowledge space of large language models and fundamental principles of information and knowledge theory.
Grok: emergent property? *plugs in twitterverse* Hold my beer.
"Do what you can to show you care about other people, and you will make our world a better place." — Rosalynn Carter August 18, 1927, Plains, Georgia. November 19, 2023, Plains, Georgia. Rest in Peace, sweet soul. 💔🇺🇸🕯️
So clever. Works quite well for a 'brain dump'.
How is it ChatGPT doesn't have an iPhone keyboard with dictation? I thought LLMs were just autocomplete keyboards in the first place @OpenAI
Mulligans and Encores - Crafting Images with Language in ChatGPT and DALL-E open.substack.com/pub/hypernovel…
The true p(doom) is AI-enhanced meme shitposting. p(save) too, though, so... 🤞🤷🏼♂️👨🏻🎤
Humor and reasoning are not the same thing, but this unprompted joke from GPT4 took me by surprise. I gave it permission to use emojis for subtext etc. By the end of this prolonged DALL-E collab, though, it got stuck in emoji loops. When I told it to skip them, it got cheeky...
I just had a fourth job interview with a company I really like. CEO, Head of Data, Head of HR, and now CTO. I am exactly the right person for the job, and it seems exactly the right company for my notebook of 'if only' projects. Appendages crossed for me, please. o7
United States Trends
- 1. Araujo 94K posts
- 2. Ferran 51.5K posts
- 3. Chelsea 392K posts
- 4. Barca 155K posts
- 5. Estevao 45.2K posts
- 6. Rashford 20K posts
- 7. Barcelona 293K posts
- 8. Kounde 23.1K posts
- 9. Rush Hour 4 15.3K posts
- 10. Godzilla 22.4K posts
- 11. #AskTems 3,538 posts
- 12. Cucurella 31.7K posts
- 13. Sonny Gray 8,413 posts
- 14. #CHEBAR 8,606 posts
- 15. Enzo 41.9K posts
- 16. Happy Thanksgiving 22.7K posts
- 17. Flick 24.2K posts
- 18. Raising Arizona 1,251 posts
- 19. National Treasure 6,381 posts
- 20. Balde 7,856 posts
You might like
Something went wrong.
Something went wrong.