195 mentions · 158 chunks · 69 episodes
... some friends shared with me. When driving somewhere with a kid in the car, ask ChatGPT, "Tell me about gas giants" and then help the kid ask follow-up questions. You can also ask ChatGPT to come up with some quiz questions for your kid ...
An interaction pattern I've seen people do in ChatGPT: named, thematic chats. The default style of use of ChatGPT (in my experience) is that every conversation is a new chat. A fresh sheet of paper, tota...
LLMs are inherently bland. If you ask ChatGPT to ask you an interesting question it'll say something super generic like: "What movie or book do you think everyone should read or see, and why?" LL...
...use case for users so they can get a sense of what it can do. Google Search and ChatGPT are two open-ended tools. But they are both good enough at so many things, that no matter what you do as a first use case, you're likely to have a go...
There's something clear about starting a separate conversation in e.g. ChatGPT You can see exactly what the LLM sees: what's in the conversation. You can start a fresh conversation if you want fresh context. The new ChatGPT memo...
...the ladder of savviness in an open-ended tool. in the future we'll look back at ChatGPT and be like "wow that was super slow and limited!"
... I!") A first response that is good and intriguing and invites experimentation. ChatGPT has social proof of examples of people posting great results and evangelizing them. People higher on the savviness ladder can help give encouragement...
...r day and help you distill a journal for reflection later. One way: do a GPT in ChatGPT. It's easy to do... but no way to export your journal entries anywhere. They're just stuck in chat transcripts in the system. Another way: duct tape ...
ChatGPT and LLMs have proven to be more useful to individuals than to companies. That implies that we're still in the community garden phase, not the factory...
...e. You're in the loop with the software. This solves a confusing riddle: Why is ChatGPT so compelling, but most LLM-powered UIs are underwhelming or hard to trust? In a ChatGPT conversation, you're in the loop with the LLM; you can see h...
...crap" moment. OSes do this now with system-level microphone / camera indicator. ChatGPT's new personal memory feature doesn't do this. It's possible to ask it to save little memories about you (e.g. "I typically program in Typescript"). ...
... concept, it's a good sign that there isn't a clear consensus on it in society. ChatGPT turns unknown unknowns into known unknowns. It's useful when you don't even know what questions to ask. You still don't know the answers, but at leas...
...t other users come to expect to work, too. When there's a huge first mover like ChatGPT, everyone else will be evaluated on how well they perform on queries optimized for ChatGPT primarily. If services like Gemini don't do well on those,...
...mo cars feel like animals. Raw AI foundation models feel something like plants. ChatGPT feels like a person.
A few stray thoughts on LLMs. I love using ChatGPT as a kind of family feud "what will the average (X category of person) think about this phrase". Kind of an automatic wisdom of the crowds. If you ha...
...bels as cheat codes. Talking in E-Prime is hard, an intense mental workout. But ChatGPT is really great at translating a phrase into E-Prime. It helps you practice doing it, and helps you see where you were accidentally relying on an ove...
ChatGPT doesn't feel like formulating a query, it feels like talking to a human. Google is extremely impressive at figuring out how to interpret your query. ...
I was talking to a friend who is using ChatGPT in novel ways at his startup. He is not a chemistry expert, but is now able to consume relevant chemistry papers that previously would have required ...