dpf
Re:BigCode Project Releases StarCoder: A 15B Code LLM
on Friday May 05, 2023 @06:52AM (#35827595)
code-davinci-002 is a base LM, and the other 3.5 models (text-davinci-{002,003}, gpt-3.5-turbo, and ChatGPT) use instruction tuning and/or RLHF. Source: https://platform.openai.com/docs/model-index-for-researchers
An A.I. Finally Won an Elite Crossword Tournament
Reginald Foster, Vatican Latinist Who Tweeted in the Language, Dies at 81
Re:On Chomsky and the Two Cultures of Statistical Learning (2011)
on Thursday March 01, 2018 @02:16AM (#16490253)
Previous discussion:
Ars Longa, Vita Brevis
Re:Roboschool: open-source software for robot simulation
on Monday May 15, 2017 @09:14PM (#14346665)
These environments are often used as a testbed for reinforcement learning, e.g. https://arxiv.org/abs/1502.05477