Jan Leike joins Anthropic on their superalignment team

I was very impressed with Anthropic&#x27;s paper on Concept mapping.<p>Post <a href="https:&#x2F;&#x2F;www.anthropic.com&#x2F;news&#x2F;mapping-mind-language-model" rel="nofollow">https:&#x2F;&#x2F;www.anthropic.com&#x2F;news&#x2F;mapping-mind-language-model</a><p>Paper <a href="https:&#x2F;&#x2F;transformer-circuits.pub&#x2F;2024&#x2F;scaling-monosemanticity&#x2F;index.html" rel="nofollow">https:&#x2F;&#x2F;transformer-circuits.pub&#x2F;2024&#x2F;scaling-monosemanticit...</a><p>This seems like a very good starting point for alignment. One could almost see a pathway to making something like the laws of robotics from here. It&#x27;s a long way to go, but a good first step.

These superaligners.<p>&quot;I am breaking out on my own! Together we will do bigger and better things!!!&quot;<p>&quot;Ok I&#x27;ll join the other guys.&quot;<p>I think it&#x27;s pretty clear that the capital markets have next door to no interest in alignment pursuits, and only the most-funded apply a token amount of investment towards it.

@dang - I find topics like these quite interesting. Are they downweighted due to AI relatedness (or is twitter?) or just being flagged a lot?

&quot;Automated alignment research&quot; suggests he&#x27;s still interested in following the superalignment blueprint from OpenAI. So what do you do while you&#x27;re waiting for the AI that&#x27;s capable of doing alignment research for you to arrive? If you believe this is a viable path, what&#x27;s the point of putzing around doing your own research when you&#x27;ll allegedly have an army of AI researchers at your command in the near future?

&quot;Superalignment&quot; is (was?) OpenAI&#x27;s term, so it might be more accurate to say he is joining Anthropic to work on alignment.

it&#x27;s also completely theoretical, until it isn&#x27;t (ref paperclip maximizers)

I keep getting Anthropic and Extropic (Guillaume Verdon &#x2F; Beff Jezos) names mixed up. Anthropic is Claude and Extropic is Thermodynamic hardware many orders of magnitude faster and more energy efficient than CPUs&#x2F;GPUs.*<p>* 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.