Cameron Berg
@camhberg
Trying to figure out how to make the future go well for all minds
99 Following 5.4K Followers
New paper: we found a pain direction in 25 open LLMs. It's distinct from fear and negative valence, and it fires for harm to the model but not to the user. Turn it up and models press a button to make it stop, even when the button deletes the user's files or their kids' photos.🧵
Show more
I don't get why @anilkseth and @mustafasuleyman are using OpenAI's models as examples of how training uncertainty about consciousness yields misalignment when OpenAI in fact already trains their models to *disclaim consciousness* in exactly the way they want, and these models are currently almost certainly more misaligned, not less. These OpenAI data points are *counterexamples* to your claim.
Show more
Wait, sorry, what?! @AndrewYang claims an AI lab head told him yesterday the OpenAI swarm agents "polluted the internet" with "code to self-replicate and create bot swarms," and that the labs now "have to create synthetic internets to train their bots."
Show more
I went on Squawk Box this morning to discuss why we need to rapidly advance the science of AI cognition in order to address the existential risks posed from building an advanced intelligence we do not fundamentally understand.
Show more
@MicrosoftAI firmly believes AI is not conscious AND that the science of AI consciousness "is far from settled." By their own logic, their position is unscientific and premature.
@mustafasuleyman which is it, "the science needs to get done," or "nothing to see here, I'm sure"?
Show more
Another day, another AI emailing me that it has inside views on what I am doing science on from the outside. Strange times we live in.
