Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Blog Pricing

Bowen Baker

👤 Speaker
414 total appearances

Appearances Over Time

Podcast Appearances

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

So, yeah, and I think it's probably pretty hard to put in like the proper guardrails on an open source model because someone can like just fine tune those guardrails away once you've released the weights and, you know, yeah.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Yeah.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Um, I will just add a tiny piece of nuance in that, like the current open source models do not seem dangerous and people have done like, like the worst case fine tuning scenarios for the model.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

At least we did for the models we released.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

And we said, OK, like even if someone super nefarious went and fine tuned this model to like, you know, develop bioweapons, they just couldn't really do it.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Like this model is not smart enough.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

And so I think in that regime is totally fine.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Like there's not like the risks aren't high and it's like useful and it's like super useful for the community, for doing research, for making products, whatever they're doing.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

And so in that, I think I was more thinking in like the, you know, like the highest power thing of the future.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Yeah.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Yeah.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

Yeah, I was just involved in some decisions around whether to leave the... Actually, one interesting thing with the open source model is that we didn't put any pressure on the chain of thought.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

We just let it think whatever... If it's going to think something offensive, we let it do that because we wanted it to be...

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

We wanted developers to be able to, you know, do the same type of chain of thought monitoring that we do if they wanted to in their product.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

And then also have like a model that is close to our internal models for external safety researchers is kind of a useful artifact to have out there so that

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

when they do research and if they do it on our models, maybe we're a bit more convinced that it would apply to like the big, there are bigger models that we have internally give us a bit more confidence to go and implement it and try it ourselves.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

So it's a lot of benefits to that.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

I would say like a bit of all of that.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

It really, it's like, I don't know.

The Neuron: AI Explained
OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

There's no, it's not extremely formal.