We’re starting a Fellows program to help engineers and researchers transition into doing frontier AI safety research full-time. Beginning in March 2025, we'll provide funding, compute, and research mentorship to 10–15 Fellows with strong coding and technical backgrounds.
SAFETY
-
Reward Hacking in Reinforcement Learning: Exploiting Flawed Functions
By
–
At the end of Thanksgiving holidays, I finally finished the piece on reward hacking. Not an easy one to write, phew. Reward hacking occurs when an RL agent exploits flaws in the reward function or env to maximize rewards without learning the intended behavior. This is imo a
-
Samsung See-Through Truck: Safety Innovation or Hazard?
By
–
🚛 Samsung's "See-Through" Truck: Brilliant or Dangerous?
— Pascal Bornet (@pascal_bornet) 2 décembre 2024
A truck with front cameras streaming road view to rear LED screens, helping drivers decide when it's safe to overtake. While it aims to prevent accidents, the question remains: does this tech improve safety or create more… pic.twitter.com/N87qPoKN5FSamsung's "See-Through" Truck: Brilliant or Dangerous? A truck with front cameras streaming road view to rear LED screens, helping drivers decide when it's safe to overtake. While it aims to prevent accidents, the question remains: does this tech improve safety or create more
-
AI’s Future Role in Critical Decision-Making and Disease Diagnosis
By
–
Andrej’s tweet is the right way to think about it right now but I totally believe that in one or two years we will start relying on AI for very challenging decisions like diagnosing disease under limited information. Key thing to note here is that big decisions can be viewed as a
-
Pascale Gourdeau discusses computability of robust learning
By
–
The last talk of the day, prior to some breakout sessions, is by Pascale Gourdeau, on the computability of robust learning http://
arxiv.org/abs/2406.10161 -
Trust and Safety Discussions as Key to AI Safety
By
–
Why trust and safety discussions are key to AI safety
#AI #AIio #BigData #ML #NLU #Futureofwork @TunstallAsc @StrategyFintech @TamaraMcCleary @TerenceLeungSF @psb_dc @thomaspower @vinod1975 @ylecun -
AI Scaling Laws and Biosecurity: Expert Discussion Video
By
–
in two hours, we'll publish a 45 min video discussion with a special guest on ai scaling laws and whether we're hitting a wall in the meantime, @chalmermagne are writing about ai and biosecurity: hype or cause for concern? you can follow along on press(dot)airstreet(dot)com
-
Escaping Advanced Drone Technology Challenges
By
–
Difícil escapar de uno de estos drones… 😱 pic.twitter.com/BkN8OSOhHU
— Juan Merodio (@juanmerodio) 27 novembre 2024Difícil escapar de uno de estos drones…
-
Merge Human Talent with Technology to Exceed Your Limits
By
–
Bill Gates once said, “I will always choose a lazy person to do a difficult job because a lazy person will find an easy way to do it.”
— Pascal Bornet (@pascal_bornet) 27 novembre 2024
You too can merge your unique human talents with cutting-edge technology 😉 to exceed your limits. Learn how by joining the IRREPLACEABLE… pic.twitter.com/ciF9NX5PD9Bill Gates once said, “I will always choose a lazy person to do a difficult job because a lazy person will find an easy way to do it.” You too can merge your unique human talents with cutting-edge technology to exceed your limits. Learn how by joining the IRREPLACEABLE
