Tweets
- Tweets, current page.
- Tweets & replies
- Media
You blocked @MIRIBerkeley
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @MIRIBerkeley
-
It's the final day of our 2019 fundraiser. Help MIRI grow!https://intelligence.org/2019/12/02/miris-2019-fundraiser/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Our fundraiser ends tomorrow! We need your help to continue growing in 2020.https://intelligence.org/2019/12/02/miris-2019-fundraiser/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
In this blog post, Open Philanthropy staff give their annual suggestions for individual donors:https://www.openphilanthropy.org/blog/suggestions-individual-donors-open-philanthropy-staff-2019 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
A review of AI alignment research from the past year:https://www.alignmentforum.org/posts/SmDziGM9hBjW9DKmf/2019-ai-alignment-literature-review-and-charity-comparison …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
New this month: our annual fundraiser is live, with details on new hires and other recent developments at MIRI.https://intelligence.org/2019/12/05/december-2019-newsletter/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: https://openai.com/projects/five/ One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat
@OGEsports.pic.twitter.com/1kWvXwBHHpThanks. Twitter will use this to make your timeline better. UndoUndo -
Our 2019 fundraiser is live! Over the last two years, our research team has ~doubled in size. Our goal is to raise $1M by Dec. 31, letting us go into 2020 with 1.25-1.5 years worth of reserves. Learn more about what we've been up to, and how you can help:https://intelligence.org/2019/12/02/miris-2019-fundraiser/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Tomorrow is Giving Tuesday! Help us secure up to $100,000 in matching funds on/from Facebook by donating to our Fundraiser page at exactly 5:00:00PT. More tips here:http://intelligence.org/2019/11/28/giving-tuesday-2019/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
This Tuesday, Dec. 3, is Giving Tuesday! Last year, our lightning-fast supporters helped us get $40,000 in matching from Facebook/Paypal! Help us match up to $100,000 this year with the strategy tips here:https://intelligence.org/2019/11/28/giving-tuesday-2019/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
[Alignment Newsletter #75]: Solving Atari and Go with learned game models, and thoughts from a MIRI employee - https://mailchi.mp/3e34fa1f299a/an-75-solving-atari-and-go-with-learned-game-models-and-thoughts-from-a-miri-employee …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
MIRI Retweeted
2. AI Research Needs Responsible Publication Norms—
@RebeccaCrootof in@lawfareblog:http://bit.ly/2BVOwajShow this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
"Suppose you are designing a new invention, a predict-o-matic. It is a wondrous machine which will predict everything for us..."https://www.lesswrong.com/posts/SwcyMEgLyd4C3Dern …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
AlphaStar update from
@DeepMindAI in (of course)@nature - now Grandmaster level in StarCraft IIhttps://www.nature.com/articles/s41586-019-1724-z …Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
Alignment Newsletter #69: Stuart Russell's new book on why we need to replace the standard model of AI - https://mailchi.mp/59ddebcb3b9a/an-69-stuart-russells-new-book-on-why-we-need-to-replace-the-standard-model-of-ai …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
We've fine-tuned GPT-2 using human feedback for tasks such as summarizing articles, matching the preferences of human labelers (if not always our own). We're hoping this brings safety methods closer to machines learning values by talking with humans.https://openai.com/blog/fine-tuning-gpt-2/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
We've observed AIs discovering complex tool use while competing in a simple game of hide-and-seek. They develop a series of six distinct strategies and counterstrategies, ultimately using tools in the environment to break our simulated physics:https://openai.com/blog/emergent-tool-use …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
MIRI Retweeted
In this newest episode of the AI Alignment Podcast, Stuart Armstrong discusses his recently published research agenda on how to identify and synthesize human values into a utility function.https://futureoflife.org/2019/09/17/synthesizing-a-humans-preferences-into-a-utility-function-with-stuart-armstrong/ …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.