Yusuke Oda (@odashi_en) 's Twitter Profile
Yusuke Oda

@odashi_en

Researcher@Tohoku University
Author of latexify: github.com/google/latexif…

ID: 1557310182627033089

linkhttps://github.com/odashi calendar_today10-08-2022 10:18:02

124 Tweet

634 Followers

57 Following

Inspired Cognition (@inspiredco_ai) 's Twitter Profile Photo

Hello World! We are Inspired Cognition, and our mission is to make it easy for everyone to efficiently and effectively build *reliable* AI-driven systems. We have a few announcements coming up soon, so watch this space đź‘€

Hello World! We are Inspired Cognition, and our mission is to make it easy for everyone to efficiently and effectively build *reliable* AI-driven systems. We have a few announcements coming up soon, so watch this space đź‘€
Inspired Cognition (@inspiredco_ai) 's Twitter Profile Photo

With recent AI progress, it’s never been easier to build AI-driven apps! But does your app/system work as expected? Or does it serve up false facts, incoherent gibberish, or toxic content? Introducing *Critique*, a quality-control tool for generative AI! docs.inspiredco.ai/critique/index…

With recent AI progress, it’s never been easier to build AI-driven apps! But does your app/system work as expected? Or does it serve up false facts, incoherent gibberish, or toxic content? Introducing *Critique*, a quality-control tool for generative AI! docs.inspiredco.ai/critique/index…
Yusuke Oda (@odashi_en) 's Twitter Profile Photo

davinci-functions, a library to obtain *Python literals* from GPT, is now available on PyPI: github.com/odashi/davinci…

davinci-functions, a library to obtain *Python literals* from GPT, is now available on PyPI:
github.com/odashi/davinci…
Yusuke Oda (@odashi_en) 's Twitter Profile Photo

Interesting. I wrote a function to synthesize a function using the result of GPT, and demonstrates how we could inject malicious prompts. My prompt involves a bug around os.environ (it is definitely not intended) but the result works successfully because GPT corrected it.

Interesting. I wrote a function to synthesize a function using the result of GPT, and demonstrates how we could inject malicious prompts. My prompt involves a bug around os.environ (it is definitely not intended) but the result works successfully because GPT corrected it.
Yusuke Oda (@odashi_en) 's Twitter Profile Photo

Implemented davinci_functions.function(prompt) that synthesizes Python callable from the given prompt. github.com/odashi/davinci…

Implemented davinci_functions.function(prompt) that synthesizes Python callable from the given prompt.
github.com/odashi/davinci…