this post was submitted on 12 Jun 2023
22 points (100.0% liked)
Science
13000 readers
2 users here now
Studies, research findings, and interesting tidbits from the ever-expanding scientific world.
Subcommunities on Beehaw:
Be sure to also check out these other Fediverse science communities:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
PhD student working in reinforcement learning (the branch of machine learning, not the neuroscience kind). Trying to figure out how to make more general agents, and I'm hypothesizing that making things bigger is a key ingredient.
Bigger seems to have helped so far, yeah, with things like GPT3.5 being based m some really massive models iirc? Happy to have you around!