Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents · HackerPapers discussions

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents — mentioned by visarga

Sat, 23 Jul 2022 18:00:59 GMT

You just need to put it inside a for loop to run continuously. Or put them on wheels to get prompted by the environment[1]. Or give them a game to play[2]. [1] https://arxiv.org/abs/2201.07207 [2] https://www.deepmind.com/publications/a-generalist-agent

Paper and discussion history. A mention is not an endorsement.

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents — mentioned by visarga

Thu, 14 Apr 2022 19:28:42 GMT

The advent of edge GPT-3 would be a huge change for robotics as well. It has been proven that augmenting robots with a language model for planning gives a leap in abilities. Maybe they could even enter any kitchen and make a sandwich (sudo make me a sandwich task). https://arxiv.org/pdf/2201.07207.pdf

Paper and discussion history. A mention is not an endorsement.

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents — mentioned by visarga

Tue, 05 Apr 2022 05:37:34 GMT

I think reaching AGI has to do with the 4 E's: embodied, enacted, embedded and extended. These models have no embodiment, no complex external environment, and there is no goal to attain other than language games. But they could be embodied, and some experiments have shown for example how a LM can guide an agent in a 3D virtual home to accomplish tasks. (*) Maybe AIs can be educated like children after they reach a certain threshold, by giving them robotic bodies and immersing them in the human society which is the most complex environment for intelligence. (*) Language Models as Zero-Shot…

Paper and discussion history. A mention is not an endorsement.

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents — mentioned by visarga

Mon, 24 Jan 2022 12:15:09 GMT

I think large frozen LMs are going to become the "operating system" of tomorrow. They are almost universal task solvers, with the right prompt or verbalizer. The trend now is to make them multi language, multi modal, multi task, multi memory ([1] and this paper), and scale computation with the problem complexity instead of keeping it fixed. After that the next step I think is to make LMs that map arguments to functions from unstructured input, externally run the function and use the result in the next token predictions. LMs could write functions and execute them as regular code. They could…

Paper and discussion history. A mention is not an endorsement.