Twitter | Search | |
OpenAI
OpenAI is a non-profit AI research company, discovering and enacting the path to safe artificial general intelligence. We're hiring:
362
Tweets
0
Following
308,069
Followers
Tweets
OpenAI Nov 17
We will now be accepting applications for our Winter 2019 OpenAI Scholars program until 11/30. More details:
Reply Retweet Like
OpenAI retweeted
DeepMind Nov 16
Learning to play Atari games without rewards by combining human preferences and expert demonstrations (collaboration with ):
Reply Retweet Like
OpenAI Nov 8
Releasing Spinning Up in Deep RL, a new educational package to let anyone become a deep reinforcement learning practitioner: Next year, we'll teach workshops on Spinning Up at CHAI, OpenAI, and other venues.
Reply Retweet Like
OpenAI Nov 7
We’ve built an energy-based model that can quickly recognize, generate, and transfer simple concepts after only 5 training demos:
Reply Retweet Like
OpenAI Nov 6
Introducing POLO, a framework that lets us learn tasks on the fly like humanoid locomotion and dexterous in-hand manipulation. Collaboration with the University of Washington.
Reply Retweet Like
OpenAI retweeted
Greg Brockman Oct 31
An agent which learned to play Mario without rewards. Instead, it was incentivized to avoid "boredom" (that is, getting into states where it can predict what will happen next). Discovered warp levels, how to defeat bosses, etc. More details:
Reply Retweet Like
OpenAI Oct 31
Random Network Distillation: A prediction-based method that achieves state-of-the-art performance on Montezuma’s Revenge -
Reply Retweet Like
OpenAI Oct 26
Want to help us build out our world-class team of engineers, researchers, policy experts, and more ensuring that safe artificial general intelligence benefits all of humanity? Apply to be a Recruiter at OpenAI:
Reply Retweet Like
OpenAI Oct 22
Iterated Amplification: An AI safety technique that has the potential to let us specify behaviors and goals that are beyond human scale:
Reply Retweet Like
OpenAI Oct 11
Apply for our Winter 2019 OpenAI Scholars Program, open to individuals from underrepresented groups in STEM interested in becoming deep learning practitioners -
Reply Retweet Like
OpenAI Oct 9
Come join the OpenAI team as a Fellow or Intern in 2019 — applications now open: !
Reply Retweet Like
OpenAI retweeted
Greg Brockman Sep 21
Have been making serious progress on OpenAI Five. Looking for Dota teams with average MMR 6.5k+ or Tier 3 and higher to test the latest version. Ping brooke@openai.com if you’d like to try it out!
Reply Retweet Like
OpenAI Sep 10
Neural waltzes, semantic trees, CycleGANs, and more - details on OpenAI Scholars' 2018 Final Projects: Demo day in San Francisco on September 20th!
Reply Retweet Like
OpenAI Sep 6
1. Double model size 2. Initialize from old parameters 3. 10 additional days of training Result: 80% win rate versus model that played on-stage at The International vs paiN Gaming.
Reply Retweet Like
OpenAI Aug 23
Our results at The International 2018:
Reply Retweet Like
OpenAI retweeted
Greg Brockman Aug 23
Replying to @gdb
Congratulations to Xiao8, BurNIng, rOtK, Ferrari_430, SanSheng — top-tier Dota players who defeated OpenAI Five after 45 mins of exciting gameplay. And thanks to everyone in the Dota community who watched. Looking forward to showcasing further improvements in the future!
Reply Retweet Like
OpenAI Aug 23
OpenAI Five's second match at The International will start in the next few minutes. Will be streamed on The International's Twitch channels: - English: - For newcomers:
Reply Retweet Like
OpenAI retweeted
Greg Brockman Aug 22
Congratulations to Team paiN, the Dota 2 pro team who just beat OpenAI Five in a 51 minute game. Lots of extremely exciting plays by both teams. Has been a great showcase of what both humans and AIs can do.
Reply Retweet Like
OpenAI Aug 22
OpenAI Five match starting now: !
Reply Retweet Like
OpenAI Aug 22
First OpenAI Five match at The International today! - Streamed on The International's Twitch channels. English: . For newcomers: - Held at the end of today's 1p PT matches — likely be around 3p PT.
Reply Retweet Like