A recent small innovation in artificial "intelligence" was the
   publication of a system called "cibi", which autonomously wrote code in
   the dainty language "brainfuck", in a way that was competitive with
   openai's environment
   benchmarks: [1]https://arxiv.org/pdf/2101.09571v3.pdf
   The code unfortunately has been removed from
   github: [2]https://github.com/vadim0x60/cibi
   However, the author says it will be back
   soon: [3]https://github.com/vadim0x60/cibi-experiments/issues/4
   Meanwhile, if you want to write a new AI virus or try to solve
   automatic world peace in a way that actually uses transparent
   respectful communication instead of covert direct result, there are
   many other reinforcement learning approaches out there ...
   In the field of machine learning, a bit ago a group called eleuther-ai
   open sourced an alternative to the expensive private text generation
   algorithm GPT-3: [4]https://www.eleuther.ai/ The license they chose is
   MIT.
   And cell phones are making daily strides towards turning into that
   future with end-user apps, if you check the right places in the
   commercial app stores.
   I ran into an early reinforcement algorithm on facebook while
   politically targeted and now copy traumatic echoes of its patterns with
   my behavior everywhere.  It was mostly about covering itself up.
   Apparently it's a big thing to have unsupervised reinforcement learning
   algorithms "accidentally" mind control people; it's like a serious
   problem actually being studied, if you look into the field of
   alignment.  It's one of many problems that are being cast as pretty
   hard to mathematically avoid.

References

   1. https://arxiv.org/pdf/2101.09571v3.pdf
   2. https://github.com/vadim0x60/cibi
   3. https://github.com/vadim0x60/cibi-experiments/issues/4
   4. https://www.eleuther.ai/