Christine McLeavey
1,803 posts
Christine McLeavey
@mcleavey
@openai audio team: gpt-4o, jukebox & musenet
Stanford, CA
Joined April 2009
- Extremely excited to share work I've been doing at OpenAI the past few months: MuseNet, a neural net music generator. It's been a huge team effort pulling this all together!Introducing MuseNet, a neural network which discovered how to generate music using many different instruments and styles. Listen & interact: openai.com/blog/musenet/ MuseNet will play an experimental concert today from 12–3pmPT on livestream: twitch.tv/openai
00:00 - Excited to bring voice mode to ChatGPT! Amazing work by @AlecRad @_jongwook_kim @txhf @giertler @michpokrass @joannejang and many others!Replying to @OpenAIUse your voice to engage in a back-and-forth conversation with ChatGPT. Speak with it on the go, request a bedtime story, or settle a dinner table debate. Sound on 🔊
00:00 - First day full time @OpenAI! It's been quite a journey from my 1st @DeepLearningAI_ class on neural nets, to the wonderful @fastdotai diversity fellowship, to OpenAI's own scholars/fellows program. Thankful for all the support & looking forward to lots more to learn and create.
- Honored to talk w @AndrewYNg. His @DeepLearningAI_ courses were my intro to the field & I wouldn't be here w/o his clear & inspiring teaching! I think of these, the @fastdotai courses, and the @OpenAI scholars/fellows, as the 3 essential steps I've taken in this wild journeyA year ago, Christine finished the Deep Learning Specialization. Now she’s a full-time @OpenAI research scientist building neural networks that create original music. Watch @mcleavey and @AndrewYNg's chat:
00:00 - i love the openai team so much
- A painting of a sad octopus playing the guitar with seaweed in the background -- so much fun to play with the new DALL-E model & huge congrats to the whole team!
- Thrilled to introduce Jukebox, our latest work generating music, now in the raw audio domain! With @prafdhar, Heewoo Jun, and @_jongwook_kimIntroducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We're releasing a tool for everyone to explore the generated samples, as well as the model and code: openai.com/blog/jukebox/
00:00 - Just blew my 5-year-old's mind by explaining we didn't have YouTube when I was his age. He asked in total disbelief, "so what did you have on your iPad -- only Netflix?!?"
- If you’re learning a second language, I highly recommend practicing with voice mode! (I set my custom prompt so that the model knows to stay in Portuguese, but to correct my grammar if I make mistakes or teach me the translation if I drop back into English)ChatGPT with voice is now available to all free users. Download the app on your phone and tap the headphones icon to start a conversation. Sound on 🔊
00:00 - OpenAI is nothing without its people
- Google open-sources BERT, a state-of-the-art pretraining technique for natural language processing venturebeat.com/2018/11/02/goo… via @VentureBeat
