During my first 2.5 years at OpenAI, I worked on the Robotics team on a moonshot idea: we wanted to teach a single, human-like robot hand to solve Rubik’s cube. It was a tremendously exciting, challenging, and emotional experience. We solved the challenge with deep reinforcement learning (RL), crazy amounts of domain randomization, and no real-world training data. More importantly, we conquered the challenge as a team.
From simulation and RL training to vision perception and hardware firmware, we collaborated so closely and cohesively. It was an amazing experiment and during that time, I often thought of Steve Jobs’ reality distortion field: when you believe in something so strongly and keep on pushing it so persistently, somehow you can make the impossible possible.
Since the beginning of 2021, I started leading the Applied AI Research team. Managing a team presents a different set of challenges and requires working style changes. I’m most proud of several projects related to language model safety within Applied AI:
- We designed and constructed a set of evaluation data and tasks to assess the tendency of pre-trained language models to generate hateful, sexual, or violent content.
- We created a detailed taxonomy and built a strong classifier to detect unwanted content as well as the reason why the content is inappropriate.
- We are working on various techniques to make the model less likely to generate unsafe outputs.
As the Applied AI team is practicing the best way to deploy cutting-edge AI techniques, such as large pre-trained language models, we see how powerful and useful they are for real-world tasks. We are also aware of the importance of safely deploying the techniques, as emphasized in our Charter.
- SEO Powered Content & PR Distribution. Get Amplified Today.
- Platoblockchain. Web3 Metaverse Intelligence. Knowledge Amplified. Access Here.
- Source: https://openai.com/blog/the-power-of-continuous-learning
- :is
- 2021
- a
- AI
- ai research
- amazing
- amounts
- and
- applied
- Applied AI
- ARE
- AS
- At
- Beginning
- believe
- BEST
- built
- CAN
- challenge
- challenges
- challenging
- Changes
- closely
- collaborated
- content
- continuous
- created
- cutting-edge
- data
- deep
- deploy
- deploying
- designed
- detailed
- different
- domain
- during
- emphasized
- evaluation
- exciting
- experience
- experiment
- First
- For
- generate
- hand
- Hardware
- How
- HTTPS
- i
- idea
- importance
- impossible
- in
- IT
- jpg
- Keep
- language
- large
- leading
- learning
- likely
- make
- managing
- model
- models
- more
- most
- of
- on
- OpenAI
- perception
- persistently
- plato
- Plato Data Intelligence
- PlatoData
- possible
- power
- powerful
- presents
- projects
- proud
- Pushing
- real world
- reason
- related
- requires
- research
- robot
- robotics
- safely
- Safety
- set
- several
- Sexual
- simulation
- single
- So
- SOLVE
- something
- started
- Steve
- strong
- strongly
- style
- such
- tasks
- taxonomy
- team
- techniques
- that
- The
- thought
- time
- to
- Training
- tremendously
- unwanted
- various
- vision
- wanted
- Way..
- WELL
- Wikipedia
- with
- within
- worked
- working
- years
- You
- zephyrnet