andrew gao's banner

andrew gao

@itsandrewgao • 40,805 subscribers

@cognition @stanford; prev @sequoia @LangChainAI @pika_labs @nomic_ai; Z Fellow 🇺🇸; views my own

Shorts

you can instantly 10x your vibecoded frontends by just learning what different ui components are called ofc opus is creating generic slop, the only words you know are menu and button.

you can instantly 10x your vibecoded frontends by just learning what different ui components are called ofc opus is creating generic slop, the only words you know are menu and button.

1,821,697 просмотров

WTF: Mind reading is here. Researchers invented a new #AI method to convert brain signals into video. See the results for yourself Published in Nature yesterday: What are the implications? Is this the biggest paper of 2023? #CEBRA

WTF: Mind reading is here. Researchers invented a new #AI method to convert brain signals into video. See the results for yourself Published in Nature yesterday: What are the implications? Is this the biggest paper of 2023? #CEBRA

679,217 просмотров

more frontend vibecoding tips (results below): WHY YOUR VIBECODED FRONTENDS ALL LOOK THE SAME AND SUCK: when asked to make a frontend, the agent/llm will default to the center/average of its training data (in a very loose sense). through the training process, the model essentially converges on some default UI style. it's very capable of doing things that are different from this style, but you have to ask! for instance, ChatGPT tends to reply in the same tone for all users untill you interact with it and instruct it differently ("be sassy", "eli5"). the second reason is that most of us are not good at coming up with designs and describing them precisely (see my tweet on a crash course in common components, which i'll link below). treat frontend generation just like any other eng task! you need to provide a good detailed spec. TIPS: 1. give ur agent screenshots of designs you like (you may not know the right words to describe them but the agent will! a pic = 1000 words) where to find ui inspo? Behance, Dribbble, Mobbin (Mobbin is paid but worth it!) 2. ask ur agent for proposals, this helps "seed" different directions so the final frontend stands out. don't be afraid to go back and forth. 3. ban certain tendencies: no Inter/Roboto, no shadcn (controversial), no gradients, no emojis 4. encourage the agent to be extreme and make bold decisions, not safe ones. i think that the underlying models tend to get taught during RL/fine-tuning to make conservative choices that produce reasonable but boring frontends 5. give ur agent Figma MCP. the best results will come if you mockup your vision in Figma first. 6. Ideally choose an agent with vision capabilities TLDR: Most people are tremendously underusing agents for frontend design. They are much better than you might expect.

more frontend vibecoding tips (results below): WHY YOUR VIBECODED FRONTENDS ALL LOOK THE SAME AND SUCK: when asked to make a frontend, the agent/llm will default to the center/average of its training data (in a very loose sense). through the training process, the model essentially converges on some default UI style. it's very capable of doing things that are different from this style, but you have to ask! for instance, ChatGPT tends to reply in the same tone for all users untill you interact with it and instruct it differently ("be sassy", "eli5"). the second reason is that most of us are not good at coming up with designs and describing them precisely (see my tweet on a crash course in common components, which i'll link below). treat frontend generation just like any other eng task! you need to provide a good detailed spec. TIPS: 1. give ur agent screenshots of designs you like (you may not know the right words to describe them but the agent will! a pic = 1000 words) where to find ui inspo? Behance, Dribbble, Mobbin (Mobbin is paid but worth it!) 2. ask ur agent for proposals, this helps "seed" different directions so the final frontend stands out. don't be afraid to go back and forth. 3. ban certain tendencies: no Inter/Roboto, no shadcn (controversial), no gradients, no emojis 4. encourage the agent to be extreme and make bold decisions, not safe ones. i think that the underlying models tend to get taught during RL/fine-tuning to make conservative choices that produce reasonable but boring frontends 5. give ur agent Figma MCP. the best results will come if you mockup your vision in Figma first. 6. Ideally choose an agent with vision capabilities TLDR: Most people are tremendously underusing agents for frontend design. They are much better than you might expect.

63,814 просмотров

arena mode party ft robot boxing

arena mode party ft robot boxing

11,548 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Very, very, very impressed by Google I/O today. Highlights: #Veo, AI video generator (1080p, more than a minute), working with donald (Childish Gambino) Gemini 1.5 Pro (GPT4-level model) with 2 million tokens Google Search now has an agent built in to do complex searches Text to Music AI Sandbox, working with Wyclef Jean Imagen 3, DALLE3/4 level model Astra Links to everything in 🧵

Very, very, very impressed by Google I/O today. Highlights: #Veo, AI video generator (1080p, more than a minute), working with donald (Childish Gambino) Gemini 1.5 Pro (GPT4-level model) with 2 million tokens Google Search now has an agent built in to do complex searches Text to Music AI Sandbox, working with Wyclef Jean Imagen 3, DALLE3/4 level model Astra Links to everything in 🧵

301,459 просмотров • 2 лет назад

i vibecoded a fully working terminal from scratch using parallel remote agents, w/o editing a single line of code. took the best agent just ~6 hrs would take me ~6-12 mo to do the same by hand w/o ai the terminal def has bugs (i posted the gh link in the article so you can test it) but can run opencode, claude code, etc! i've been able to replace iterm with it. wrote up a guide for Extreme Vibecoding with Remote Agents👇

i vibecoded a fully working terminal from scratch using parallel remote agents, w/o editing a single line of code. took the best agent just ~6 hrs would take me ~6-12 mo to do the same by hand w/o ai the terminal def has bugs (i posted the gh link in the article so you can test it) but can run opencode, claude code, etc! i've been able to replace iterm with it. wrote up a guide for Extreme Vibecoding with Remote Agents👇

57,629 просмотров • 3 месяцев назад

so it turns out you actually *can* one-shot vibecode DoorDash i gave my coding agent access to Vercel, Supabase, and Exa MCP and it figured everything out. it also tested its own work using its computer. this is not just a frontend that only works in localhost but a functional live platform where you can actually sign up as a user, driver, or restaurant. and things actually work (ok obviously it's not 1:1 doordash, there's no payments, driver tracking, etc but this very well would have been perfectly usable in 2014)

so it turns out you actually can one-shot vibecode DoorDash i gave my coding agent access to Vercel, Supabase, and Exa MCP and it figured everything out. it also tested its own work using its computer. this is not just a frontend that only works in localhost but a functional live platform where you can actually sign up as a user, driver, or restaurant. and things actually work (ok obviously it's not 1:1 doordash, there's no payments, driver tracking, etc but this very well would have been perfectly usable in 2014)

48,541 просмотров • 3 месяцев назад

Someone AI voice cloned Biden Obama and Trump and made them play Minecraft #ai #chatgpt #gpt4

Someone AI voice cloned Biden Obama and Trump and made them play Minecraft #ai #chatgpt #gpt4

168,830 просмотров • 3 лет назад

📣 Introducing FilmForge 🪄: prompt to video (check out more samples in the🧵)! 📹 Instantly create videos about anything. 🖼 Includes graphics, captions, voiceovers, transitions, and music! 🔁 Retweet for early access. 🛠 Made with OpenAI

📣 Introducing FilmForge 🪄: prompt to video (check out more samples in the🧵)! 📹 Instantly create videos about anything. 🖼 Includes graphics, captions, voiceovers, transitions, and music! 🔁 Retweet for early access. 🛠 Made with OpenAI

26,116 просмотров • 3 лет назад

!! #devin SCREENSHARE walkthrough vid! highly requested :) enjoy! lmk what i should ask @cognition devin for next...

!! #devin SCREENSHARE walkthrough vid! highly requested :) enjoy! lmk what i should ask @cognition devin for next...

18,761 просмотров • 2 лет назад

💡🚨 AI for #Consulting! Get an edge on interviews by practicing case studies with #AI! Check out the demo vid 👇📽️ McKeansey (my middle name) is powered by @openai #GPT4 and speech recognition. 🎙️ RT for free beta access in ur DM #bain @bcg @mckinsey @deloitte #chatgpt #code

💡🚨 AI for #Consulting! Get an edge on interviews by practicing case studies with #AI! Check out the demo vid 👇📽️ McKeansey (my middle name) is powered by @openai #GPT4 and speech recognition. 🎙️ RT for free beta access in ur DM #bain @bcg @mckinsey @deloitte #chatgpt #code

14,032 просмотров • 3 лет назад

Больше нет контента для загрузки