Eric Ho

@eric_ho

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

San Francisco

goodfire.ai

Joined September 2011

Replies Reposts Media

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
19
Eric Ho
@eric_ho
Sep 6
i am confident that we can solve interp but i wish we had more time
Kevin Liu
@kliu128
Sep 6
Today we're releasing data on models accelerating research at OpenAI. Recursive self-improvement could be the most important contributor to AI capabilities over the next few years, but by default it will only be seen inside a few frontier AI labs. Being transparent is more
5
Eric Ho
@eric_ho
Sep 6
understanding this alien mind is the most important problem in the world
Jakub Pachocki
@merettm
Sep 6
I wrote about the state of AI, why I’m concerned about the next few years, and the choices we need to make to keep the future in humanity’s hands. An Alien Mind: openai.com/index/an-alien…
18
Eric Ho
@eric_ho
Sep 3
excellent episode with goodfire chief scientist @banburismus_ talking about optimism for interpretability on MLST!
Goodfire
@GoodfireAI
Sep 3
"Why am I optimistic about interpretability? It's partly because I think we're starting to have really good traction - but also because I can imagine this incredible speedup." Catch our Chief Scientist @banburismus_ on the latest episode of @MLStreetTalk!
00:00
Eric Ho
@eric_ho
Sep 2
this is a good prediction. i'm confident we're going to get pareto optimal interp monitoring in < 1 year keep in mind though that these methods are additive, you generally want to do both, with a cheap activation monitor escalating to a cot monitor
roon
@tszzl
Sep 2
Replying to @tszzl
*monitor-ability* is the invariant that must be preserved, and the real solution will be via strong mechanistic interpretability. i predict in the next year there’ll be mechinterp monitoring that’s pareto optimal to cot monitors
3