🇮🇪 BREAKING: A new poll by Irish newspaper ‘The Liberal’ suggests that Conor McGregor is on course to win Ireland’s Presidential Election in a LANDSLIDE.
Almost 60% of respondents said they plan to vote for him in next month’s Election.
WOW. This would be HUGE for Ireland! 🔥🔥
This clip is worth more than $100 billion worth of campaign ads
This will go down in history beside George Washington crossing the Delaware river
Lincoln’s Gettysburg address
MLK’s “I have a Dream”
JFK’s “Ask not what your country can do for you…”
Reagan’s “Tear down this wall”
Trump rising up from near death with blood on his face and a clenched fist yelling “FIGHT! FIGHT! FIGHT”
We watched history unfold before our eyes and we will finish the job in November
Stepping away from this job has been one of the hardest things I have ever done, because we urgently need to figure out how to steer and control AI systems much smarter than us.
An *exclusive* from me about a new startup, @synth_labs, which is working to help companies get their AI systems do what they want (and avoid doing what they don't want). https://t.co/5V7SBZDUkD via @technology
Can GPT-4 teach a robot hand to do pen spinning tricks better than you do?
I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API!
Eureka bridges the gap between high-level reasoning (coding) and low-level motor control. It is a “hybrid-gradient architecture”: a black box, inference-only LLM instructs a white box, learnable neural network. The outer loop runs GPT-4 to refine the reward function (gradient-free), while the inner loop runs reinforcement learning to train a robot controller (gradient-based).
We are able to scale up Eureka thanks to IsaacGym, a GPU-accelerated physics simulator that speeds up reality by 1000x. On a benchmark suite of 29 tasks across 10 robots, Eureka rewards outperform expert human-written ones on 83% of the tasks by 52% improvement margin on average. We are surprised that Eureka is able to learn pen spinning tricks, which are very difficult even for CGI artists to animate frame by frame!
Eureka also enables a new form of in-context RLHF, which is able to incorporate a human operator’s feedback in natural language to steer and align the reward functions. It can serve as a powerful co-pilot for robot engineers to design sophisticated motor behaviors.
As usual, we open-source everything! Welcome you all to check out our video gallery and try the codebase today: https://t.co/BHiNmqPoWE
Paper: https://t.co/bdh9TYQtHm
Code: https://t.co/lqKiaM2yYJ
Deep dive with me: 🧵
For years Gavin Newsom has blamed the homeless crisis on local officials or on the complexity of the system itself, even though he controls it all as the boss of a one-party state. Now he has proven that he can fix it if he wants to. No more excuses.
Chelsea are in concrete talks with Frank Lampard to become caretaker manager until the end of the season 🚨🔵 #CFC
Discussions with Julian Nagelsmann and Luis Enrique continue for future project.
Lampard, 100% prepared to accept the job.
Final green light, up to the board.