Comment by andsoitis
6 days ago
> They're actively trying to use lobbying power to make open weight models illegal.
What is your evidence?
6 days ago
> They're actively trying to use lobbying power to make open weight models illegal.
What is your evidence?
Dario’s own mouth https://x.com/coinbureau/status/2071330294452666695/mediavie...
He has also been telling bald-faced lies about open source/open weights models that are easily disproved. For example, he claimed that they lack the collaborative benefits of open source because "we can't see inside the model".
Open weights models are responsible for enabling reams of research on interpretability methods that do just that. And they have facilitated so much collaboration on architecture, inference optimizations, training and steering methods, and other topics that were completely out of reach with closed models like Anthropic's. It's really staggering to me.
Doesn’t this seem true / self-evident:
“His warns that once powerful models are released openly, companies lose the ability to monitor misuse, revoke access, or update safety guardrails.”
2 replies →
Yeesh. “What shall we do sire, when the peasants learn to read?” vibes
You mean to tell me that anyone can own a nail-gun? We can't have people buying their own nail-guns, next thing you know they might build things that aren't up to code!
This does not load (or no longer loads) over here.
https://x.com/coinbureau/status/2071330294452666695
that link doesn't exist anymore? what did it say?
Strange, it opens just fine...as long as you aren't logged in (to X).
1 reply →
Works for me
https://www.judiciary.senate.gov/imo/media/doc/2023-07-26_-_... https://xcancel.com/coinbureau/status/2071330294452666695 https://www.techpolicy.press/transcript-senate-hearing-on-pr...
> "Once the weights of a model are public, they cannot be retrieved. If a model possesses dangerous capabilities, it is permanently out in the wild... We need to consider regulatory frameworks that account for the unique risks of open-source distribution of highly capable frontier models."
That's true I guess. If someone decides a model needs more guard rails, anthropic can adjust it, whereas with open weights it's too late.
It definitely sounds like the kind of thing that ends the world in B sci-fi thrillers.
Curious if I'm being downvoted by people who think there will never be a model with dangerous capabilities? Or people who think when it happens we shouldn't add guard rails?