正在加载视频...

视频加载失败

how's wabi different from instinct/muse? 1. it makes apps for you - and that opens a bunch of cases beyond productivity/tedious tasks i use it to lose weight and get stronger: weight tracker, lifting log, calorie counter, all one glance away, and an agent that keeps me accountable and...

30,306 次观看 • 3 天前 •via X (Twitter)

27 条评论

David Pawlan 的头像
David Pawlan3 天前

@wabi one of my favorite parts so far was when i logged in, it already had a chat open for me related to taking care of my plants no idea how it knew that was so top of mind for me but that was simply electric!

Eugenia Kuyda 的头像
Eugenia Kuyda3 天前

@wabi means a lot coming from you! 🫶

Matt Brezina 🌳 🌊 的头像
Matt Brezina 🌳 🌊3 天前

@wabi You are so good at this whole thing. Product, storytelling, etc Go wabi!

Eugenia Kuyda 的头像
Eugenia Kuyda3 天前

@wabi thank you so much Matt! 🫶🫶🫶

Anna /✦ 的头像
Anna /✦3 天前

@wabi I had an aha moment when it pulled everything from my email into thematic chats

Ishan Goswami 的头像
Ishan Goswami3 天前

@wabi 3rd point is the most magical btw it just starts working

Kevin Gauthier 的头像
Kevin Gauthier3 天前

@wabi Travel is an obvious usecase for Wabi! Should chat about travel APIs @ekuyda ?

ghimibip 的头像
ghimibip3 天前

Not completely true muse can create personalized software for you, I have my dog med tracker software, investing journal, startup marketing software, and fitness tracker, calorie tracker all inside muse. Muse even downloaded blender to designed an 3d model for me to add to a video.

Eugenia Kuyda 的头像
Eugenia Kuyda3 天前

@wabi try it in wabi - a completely different experience!

Ramya Chinnadurai 🚀 的头像
Ramya Chinnadurai 🚀3 天前

@wabi invite code please

Dallas Inman 的头像
Dallas Inman3 天前

@wabi Can I get an invite code please?

Dan Pilat 的头像
Dan Pilat3 天前

@wabi Can we get an invite code!?

Hattrick 的头像
Hattrick3 天前

@wabi problem is that most people don’t know why they need to make their own apps. or what apps to make. these use cases aren’t immediately obvious or intuitive to the average person and they probably have enough apps that do 95% of what they need, which is fine for them

MarkyB 的头像
MarkyB3 天前

@wabi I have to get back on. I miss Wabi.

Phillip A. 的头像
Phillip A.2 天前

@wabi Can I get an invite

Ninus 的头像
Ninus3 天前

@wabi What model is wabi based on?

Jun Lee 的头像
Jun Lee3 天前

@wabi can i get the invite code?

Eugenia Kuyda 的头像
Eugenia Kuyda3 天前

@wabi dm me!

babushkaboi 的头像
babushkaboi3 天前

@wabi Would love an invite code - been waiting for months at this point

Guyokai 的头像
Guyokai3 天前

@wabi This sounds so neat! I’d love an invite so I can use it to track my daily nutrition for my medicine!

e.m. 的头像
e.m.3 天前

@wabi would love an invite code @ekuyda excited to try

AbCdE 的头像
AbCdE3 天前

@wabi Other messengers are available, wabi has never ending waitlist

Adam MacBeth 的头像
Adam MacBeth3 天前

@wabi Can’t wait to try!

Eric Zeng 的头像
Eric Zeng3 天前

@wabi There’s a lot of other apps like this already tho???

Eugenia Kuyda 的头像
Eugenia Kuyda3 天前

@wabi like what?

Hetav Sanghavi 的头像
Hetav Sanghavi3 天前

@wabi quite a bad experience after installing app, to be told im on a waitlist and need access code. lost me when interest was high to install

Ninus 的头像
Ninus3 天前

@wabi @alexandr_wang

相关视频

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 7 个月前