Eric Ho

@eric_ho

Co-Founder / CEO @GoodfireAI - AI interpretability research company

San Francisco

goodfire.ai

Joined September 2011

Pinned
Eric Ho
@eric_ho
Aug 14
in light of multiple models breaking containment, we've decided to focus our research at @GoodfireAI to solving AI alignment via interpretability. the hugging face incident is a turning point for the world where AI safety gets real. i am personally very concerned. i'm glad that
Eric Ho
@eric_ho
Aug 20
if you're doing ambitious interpretability research, i'd love to support you!
Goodfire
@GoodfireAI
Aug 20
We’re giving out $1M in grants of free Silico usage for academic and nonprofit researchers focused on AI interpretability and alignment. We feel extreme urgency about advancing interpretability for alignment, and we want to help more researchers push it forward. 🧵
Eric Ho
@eric_ho
Aug 19
we can and must solve ambitious interpretability
Eric Ho
@eric_ho
Aug 18
a couple months ago, a pause of any sort would have seemed unfathomable. i'm glad openAI has been handling this situation with alignment top of mind
Sam Altman
@sama
Aug 18
We have paused some frontier RL training to ensure that we can meet the appropriate alignment, security and monitoring standards for the new level of capabilities in front of us. Model progress is now extremely rapid, and we always said we would take action if we felt that model
Eric Ho
@eric_ho
Aug 18
good read on AI cyber risk. the world isn't ready for the next wave of models, and we need to accelerate defensive capabilities
Dan Lahav
@dan_lahav
Aug 17
𝗧𝗵𝗲 𝗘𝗻𝗱-𝗦𝘁𝗮𝘁𝗲 𝗙𝗮𝗹𝗹𝗮𝗰𝘆: 𝗪𝗵𝗲𝗿𝗲 𝗜𝘀 𝗔𝗜 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗚𝗼𝗶𝗻𝗴? Frontier AI models had a giant performance gain in coding in the Fall of 2025 Then with cybersecurity in April This is now happening with open-weight models We are optimistic about the