Erik Jenner
@ejnnr.bsky.social
Reposted by Erik Jenner
New work from my team at Anthropic in collaboration with Redwood Research. I think this is plausibly the most important AGI safety result of the year. Cross-posting the thread below:
December 18, 2024 at 5:47 PM
New work from my team at Anthropic in collaboration with Redwood Research. I think this is plausibly the most important AGI safety result of the year. Cross-posting the thread below:
My first podcast appearance! Thanks to @danielfilan.com
for asking lots of great questions about our interpretability paper on learned look-ahead in a chess network. I'll be presenting a poster at NeurIPS tomorrow 4:30pm (East, #2802), stop by if you want to chat! axrp.net/episode/2024...
for asking lots of great questions about our interpretability paper on learned look-ahead in a chess network. I'll be presenting a poster at NeurIPS tomorrow 4:30pm (East, #2802), stop by if you want to chat! axrp.net/episode/2024...
38.3 - Erik Jenner on Learned Look-Ahead
YouTube link
axrp.net
December 12, 2024 at 6:04 AM
My first podcast appearance! Thanks to @danielfilan.com
for asking lots of great questions about our interpretability paper on learned look-ahead in a chess network. I'll be presenting a poster at NeurIPS tomorrow 4:30pm (East, #2802), stop by if you want to chat! axrp.net/episode/2024...
for asking lots of great questions about our interpretability paper on learned look-ahead in a chess network. I'll be presenting a poster at NeurIPS tomorrow 4:30pm (East, #2802), stop by if you want to chat! axrp.net/episode/2024...