News for hackers. Stuff that matters.

A comment on OpenAI: Introducing SuperAlignment. Parent comment

Re:OpenAI: Introducing SuperAlignment by DennisP on Wednesday July 05, 2023 @04:24PM (#36606575)
To save others the trouble, I googled Voyager, it's pretty interesting. I had no idea an LLM could do this sort of thing:

https://voyager.minedojo.org/

[ Parent | on HN ]
Re:OpenAI: Introducing SuperAlignment by og_kalu on Wednesday July 05, 2023 @04:58PM (#36607010)
Other examples(in the real world) you might find interesting.

https://tidybot.cs.princeton.edu/ https://innermonologue.github.io/

https://palm-e.github.io/

https://www.microsoft.com/en-us/research/group/autonomous-sy...

[ Parent | on HN ]
Re:OpenAI: Introducing SuperAlignment by Animats on Wednesday July 05, 2023 @05:11PM (#36607182)
> https://palm-e.github.io/

The alignment problem will come up when the robot control system notices that the guy with the stick is interfering with the robot's goals.

[ Parent | on HN ]
Re:OpenAI: Introducing SuperAlignment by c_crank on Wednesday July 05, 2023 @05:18PM (#36607288)
A robot control system without a mechanical override in favor of the stick is a poor one indeed.
[ Parent | on HN ]
Re:OpenAI: Introducing SuperAlignment by yldedly on Thursday July 06, 2023 @03:24AM (#36612456)
Voyager is pretty cool, but it's not transferable to the real world at all. The automatic curriculum relies on lots of specific knowledge from people talking about how to get better at Minecraft. The skill library writes programs using the Mineflayer API, which provides primitives for all physics, entities, actions, state etc. A real-life analogue of that would be like solving robotics and perception real quick.
[ Parent | on HN ]