Jackson Kernion
@jacksonkernion.bsky.social
Now: LLM finetuning, human feedback at
Anthropic. Before: MIT postdoc, UC Berkeley philosophy PhD. Built http://deductivelogic.org
Anthropic. Before: MIT postdoc, UC Berkeley philosophy PhD. Built http://deductivelogic.org
Ocean Beach in February
March 3, 2025 at 1:20 AM
Ocean Beach in February
SF in February is so pleasant
February 23, 2025 at 5:39 AM
SF in February is so pleasant
SF in January is so pleasant
January 12, 2025 at 5:43 PM
SF in January is so pleasant
RL'd LLMs can learn *anything*, so long as you can reliably evaluate 'correct' behavior and have enough examples/compute.
I think the most important question now is: how does performance on arbitrary cognitive tasks correlate with RL'd cognition?
I think the most important question now is: how does performance on arbitrary cognitive tasks correlate with RL'd cognition?
December 21, 2024 at 4:26 PM
RL'd LLMs can learn *anything*, so long as you can reliably evaluate 'correct' behavior and have enough examples/compute.
I think the most important question now is: how does performance on arbitrary cognitive tasks correlate with RL'd cognition?
I think the most important question now is: how does performance on arbitrary cognitive tasks correlate with RL'd cognition?
SF in December is so pleasant
December 5, 2024 at 10:00 PM
SF in December is so pleasant