Jan Leike joins Anthropic on their superalignment team
1–10 of 39 posts
Re: Jan Leike joins Anthropic on their superalignment team
#2"Superalignment" is (was?) OpenAI's term, so it might be more accurate to say he is joining Anthropic to work on alignment.
Re: Jan Leike joins Anthropic on their superalignment team
#3"Superalignment" is (was?) OpenAI's term, so it might be more accurate to say he is joining Anthropic to work on alignment.
Is there a difference between "superalignment" and "alignment" ?
Re: Jan Leike joins Anthropic on their superalignment team
#4I keep getting Anthropic and Extropic (Guillaume Verdon / Beff Jezos) names mixed up. Anthropic is Claude and Extropic is Thermodynamic hardware many orders of magnitude faster and more energy efficient than CPUs/GPUs.*
* parameterized stochastic analog circuits that implement energy-based models (EBMs). Stochastic computing is a computing paradigm that represents numbers using the probability of ones in a bitstream.
Re: Jan Leike joins Anthropic on their superalignment team
#5"Superalignment" is (was?) OpenAI's term, so it might be more accurate to say he is joining Anthropic to work on alignment.
Is there a difference between "superalignment" and "alignment" ?
i suppose the difference between imaginary and "super"-imaginary isn't very important from a practical point of view.
they worry about alignment for ai, I worry about alignment for the corporations that wield technology, any technology.
Re: Jan Leike joins Anthropic on their superalignment team
#6"Superalignment" is (was?) OpenAI's term, so it might be more accurate to say he is joining Anthropic to work on alignment.
Looks like superalignment was Jan Leike's term, since the team at OpenAI dissolved immediately without him.
Re: Jan Leike joins Anthropic on their superalignment team
#7"Superalignment" is (was?) OpenAI's term, so it might be more accurate to say he is joining Anthropic to work on alignment.
Is there a difference between "superalignment" and "alignment" ?
Yes. “Superalignment” (admittedly a corny term) refers to the specific case of aligning AI systems that are more intelligent than human beings. Alignment is an umbrella term which can also refer to basic work like fine-tuning an LLM to follow instructions.
Re: Jan Leike joins Anthropic on their superalignment team
#8"Automated alignment research" suggests he's still interested in following the superalignment blueprint from OpenAI. So what do you do while you're waiting for the AI that's capable of doing alignment research for you to arrive? If you believe this is a viable path, what's the point of putzing around doing your own research when you'll allegedly have an army of AI researchers at your command in the near future?
Re: Jan Leike joins Anthropic on their superalignment team
#9it's also completely theoretical, until it isn't (ref paperclip maximizers)
Re: Jan Leike joins Anthropic on their superalignment team
#10I keep getting Anthropic and Extropic (Guillaume Verdon / Beff Jezos) names mixed up. Anthropic is Claude and Extropic is Thermodynamic hardware many orders of magnitude faster and more energy efficient than CPUs/GPUs.* * parameterized stochastic analog circuits that implement energy-based models (EBMs). Stochastic computing is a computing paradigm that represents numbers using the probability of ones in a bitstream.
> Thermodynamic hardware many orders of magnitude faster and more energy efficient than CPUs/GPUs.
I’m sorry, but is this thermodynamic hardware real? Are there any benchmarks? Those claims are pretty strong.