Many users praise GoodfireAI's Silico private beta for making advanced AI experimentation more accessible to research teams and arriving at the right time to address interpretability bottlenecks.
Based on 8 visible X reactions from 19 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@bryancsk Pangram’s work is super cool! And exactly the type of research we want to enable with Silico
@_xjdr "no idea if it actually works as shown in the video" bro stop making noise then jfc
@GoodfireAI This makes complex AI experimentation far more accessible for research teams.
@GoodfireAI very cool!
The platform automates complex model interpretability and training and experiments.
@bryancsk Pangram’s work is super cool! And exactly the type of research we want to enable with Silico
@_xjdr "no idea if it actually works as shown in the video" bro stop making noise then jfc
@GoodfireAI very cool
This looks absolutely insane and is one of the first pieces of software that I think will genuinely change ML research processes. Wonder how much harnessing is needed or are the models just able to do this? Is this a Goodfire specific training stack? https://twitter.com/goodfireai/status/2077073005088501780
my boy is in there somewhere!! joking aside, this is an amazing steering system from Goodfire. Really impressive. https://x.com/andrew_n_carr/status/2077093745330405430/photo/1 https://twitter.com/GoodfireAI/status/2077073005088501780
silico is really great! if you do ai research you’ll probably find it a big uplift over cc/codex, especially for interpretability https://twitter.com/GoodfireAI/status/2077073005088501780
this is the first frontier quality research tool i've seen made available to the public. very cool to see https://twitter.com/GoodfireAI/status/2077073005088501780
Incredible. a near-frontier model we need research for direct J-space optimization now https://twitter.com/GoodfireAI/status/2077073005088501780
no idea if it actually works as shown in the video in practice, but the concepts, flow, visuals, etc. are what i am referring to here
if you want to try silico (and you should!) you can sign up here https://twitter.com/GoodfireAI/status/2077073099493912943
Many users praise GoodfireAI's Silico private beta for making advanced AI experimentation more accessible to research teams and arriving at the right time to address interpretability bottlenecks.
Based on 8 visible X reactions from 19 accounts; directional sample.
Ask a question below.
Published answers will appear here.
This looks absolutely insane and is one of the first pieces of software that I think will genuinely change ML research processes. Wonder how much harnessing is needed or are the models just able to do this? Is this a Goodfire specific training stack? https://twitter.com/goodfireai/status/2077073005088501780
my boy is in there somewhere!! joking aside, this is an amazing steering system from Goodfire. Really impressive. https://x.com/andrew_n_carr/status/2077093745330405430/photo/1 https://twitter.com/GoodfireAI/status/2077073005088501780
silico is really great! if you do ai research you’ll probably find it a big uplift over cc/codex, especially for interpretability https://twitter.com/GoodfireAI/status/2077073005088501780
this is the first frontier quality research tool i've seen made available to the public. very cool to see https://twitter.com/GoodfireAI/status/2077073005088501780
Incredible. a near-frontier model we need research for direct J-space optimization now https://twitter.com/GoodfireAI/status/2077073005088501780
no idea if it actually works as shown in the video in practice, but the concepts, flow, visuals, etc. are what i am referring to here