Josh

@josh_bickett • 8,387 subscribers

CEO @hyperwriteai @othersideai. Building the best predictive writing model. Always learning. May the best ideas win.

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

Fable 5 is insanely good at decoding the first letter of each word and guessing what I'm trying to say me: "iattfloewitsaiwytgwiw" Fable 5: "I am typing the first letter of every word in this sentence and I want you to guess what I wrote"

Fable 5 is insanely good at decoding the first letter of each word and guessing what I'm trying to say me: "iattfloewitsaiwytgwiw" Fable 5: "I am typing the first letter of every word in this sentence and I want you to guess what I wrote"

288,175 görüntüleme • 8 gün önce

𝗪𝗲 𝗮𝗿𝗲 𝗲𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝘁𝗵𝗲 𝗦𝗲𝗹𝗳-𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 𝘁𝗵𝗮𝘁 𝗲𝗻𝗮𝗯𝗹𝗲𝘀 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗶𝗻𝗰𝗹𝘂𝗱𝗶𝗻𝗴 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲 𝗵𝘂𝗺𝗮𝗻-𝗹𝗶𝗸𝗲 𝗺𝗼𝘂𝘀𝗲 𝗰𝗹𝗶𝗰𝗸𝘀 𝗮𝗻𝗱 𝗸𝗲𝘆𝗯𝗼𝗮𝗿𝗱 𝗶𝗻𝗽𝘂𝘁𝘀 𝗼𝗻 𝗮 𝗰𝗼𝗺𝗽𝘂𝘁𝗲𝗿. Based on a given objective, the model estimates the correct X & Y locations for mouse clicks and the appropriate keyboard inputs at each step. A vision-based agent working at the OS level allows for maximum context and adaptability. The framework is designed to work with any vision-text multimodal model to evaluate its ability to operate a computer. While significant improvements are needed to achieve human-level performance, this code repository serves as a plugin framework. We are also excited to announce we’ll be integrating our `𝗔𝗴𝗲𝗻𝘁-𝟭` model with the framework in the coming weeks. Help us build the future of agents in public. 𝗚𝗶𝘁𝗵𝘂𝗯: 𝗛𝗲𝗿𝗲'𝘀 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗮 𝗽𝗼𝗲𝗺 𝗶𝗻 𝗚𝗼𝗼𝗴𝗹𝗲 𝗗𝗼𝗰𝘀:

𝗪𝗲 𝗮𝗿𝗲 𝗲𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝘁𝗵𝗲 𝗦𝗲𝗹𝗳-𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 𝘁𝗵𝗮𝘁 𝗲𝗻𝗮𝗯𝗹𝗲𝘀 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗶𝗻𝗰𝗹𝘂𝗱𝗶𝗻𝗴 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲 𝗵𝘂𝗺𝗮𝗻-𝗹𝗶𝗸𝗲 𝗺𝗼𝘂𝘀𝗲 𝗰𝗹𝗶𝗰𝗸𝘀 𝗮𝗻𝗱 𝗸𝗲𝘆𝗯𝗼𝗮𝗿𝗱 𝗶𝗻𝗽𝘂𝘁𝘀 𝗼𝗻 𝗮 𝗰𝗼𝗺𝗽𝘂𝘁𝗲𝗿. Based on a given objective, the model estimates the correct X & Y locations for mouse clicks and the appropriate keyboard inputs at each step. A vision-based agent working at the OS level allows for maximum context and adaptability. The framework is designed to work with any vision-text multimodal model to evaluate its ability to operate a computer. While significant improvements are needed to achieve human-level performance, this code repository serves as a plugin framework. We are also excited to announce we’ll be integrating our `𝗔𝗴𝗲𝗻𝘁-𝟭` model with the framework in the coming weeks. Help us build the future of agents in public. 𝗚𝗶𝘁𝗵𝘂𝗯: 𝗛𝗲𝗿𝗲'𝘀 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗮 𝗽𝗼𝗲𝗺 𝗶𝗻 𝗚𝗼𝗼𝗴𝗹𝗲 𝗗𝗼𝗰𝘀:

2,079,350 görüntüleme • 2 yıl önce

I created an 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗰𝗮𝗻 𝗿𝗲𝘃𝗶𝗲𝘄 𝘁𝗵𝗼𝘂𝘀𝗮𝗻𝗱𝘀 𝗼𝗳 𝗧𝘄𝗲𝗲𝘁𝘀 to identify user pain points and discover product ideas that users will pay for. I'm saving all these Tweets to a database on willpayforthis dot com. Go here to find your next project idea! Here is the AI Agent in action.

I created an 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗰𝗮𝗻 𝗿𝗲𝘃𝗶𝗲𝘄 𝘁𝗵𝗼𝘂𝘀𝗮𝗻𝗱𝘀 𝗼𝗳 𝗧𝘄𝗲𝗲𝘁𝘀 to identify user pain points and discover product ideas that users will pay for. I'm saving all these Tweets to a database on willpayforthis dot com. Go here to find your next project idea! Here is the AI Agent in action.

437,215 görüntüleme • 1 yıl önce

Can GPT-4-Vision Play Super Mario 64? I created 'Multimodal Gamer,' a framework enabling multi-modal models (combining text and visual inputs) to play games. Check out my video overview below and let me know your thoughts!

Can GPT-4-Vision Play Super Mario 64? I created 'Multimodal Gamer,' a framework enabling multi-modal models (combining text and visual inputs) to play games. Check out my video overview below and let me know your thoughts!

22,233 görüntüleme • 2 yıl önce

Daha fazla içerik yok.