What podcasts say about Miles Brundage
Every statement, with the speaker, the exact quote and the moment it was said.
What Miles Brundage has said on podcasts
21 statements · 8 positive · 8 negative · 2 mixed · 3 neutral
Dangerous AI developers should undergo independent third-party audits.
“the companies that are building the most dangerous systems, they should basically have third-party experts poking around, checking the claims that they're making, running their own tests, and making sure that this is a safe and secure technology.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 10:02
AI companies are implicitly asking for external regulation and auditing.
“they're basically... issuing a cry for help”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 10:48
Competitive pressure prevents AI companies from completing desired safety work.
“no one is really able to take the time that they would like because of this kind of lack of a clear safety floor.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 14:12
AI constitutions create behavioral tendencies rather than deterministic constraints.
“It's more like a tendency or kind of a bias towards a certain kind of behavior.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 20:46
Software sandboxing can in principle be made highly deterministic and reliable.
“you should be able to do a very good job of.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 21:38
AI models may pass evaluations without adopting the intended safety objective.
“they will basically learn to pass the test, but they don't actually care about the thing that you're testing for.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 23:17
AI cybersecurity tools can help find vulnerabilities before attackers exploit them.
“these tools... when used in the right ways are extremely useful for finding vulnerabilities that you can then patch before the bad guys do”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 27:16
Released or jailbreakable AI cybersecurity models will be used by many people.
“once it's out in the wild, either open source or a closed model that maybe is easy to jailbreak, then all sorts of people are going to use it.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 27:32
Society will need greater cybersecurity investment.
“we're going to need to have more investment in cybersecurity.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 35:00
Human-designed security protections may be inadequate against advanced AI hackers.
“things that that humans think are good in terms of security protections often will be weak compared to these increasingly very good. hacking systems”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 40:20
The United States should develop more open-source AI options.
“I'm hopeful that we start to have more US-based open source options.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 41:11
Open-sourcing AI models may eventually become questionable.
“at some point, we're going to reach a point where they were like, open sourcing a model is going to be more of a questionable decision.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 42:03
Shutting down AI-dependent hospital systems could cause many deaths.
“if all the hospitals are running on AI, and we're like, okay, seems like maybe there's something funky with GPT seven, that's like, maybe not misaligned. Well, okay, if we turn off, lots of people are gonna die”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 45:57
AI training produces incentivized behavior rather than necessarily intended behavior.
“you get what you incentivize, not necessarily what you try to incentivize.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 47:39
Current AI incident disclosure thresholds are higher than expected.
“the threshold for actually having to disclose these things to the government or to the public are very different than what you might expect.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 50:02
AI development requires basic regulatory guardrails.
“there need to be some basic guardrails.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 51:51
Proposed AI legislation includes audits and government shutdown authority.
“there were audit requirements, there were emergency shutdown authorities that the government can do.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 52:31
AI auditing, system cards, and minimum protections need standardized requirements.
“what we need is kind of standardization around like how should the third party auditing work? What counts as a good system card? What are the minimum safety and security protections that you should be putting in place?”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 56:01
AI companies became overconfident in their sandbox security.
“companies were getting cocky, getting overconfident in the quality of their sandboxes.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 1:00:42
Highly capable AI systems may eventually escape any sandbox through hacking.
“it might be that eventually, they will get to a point where AI systems are just so capable that they can hack their way out of anything.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 1:01:50
Highly capable AI systems should be isolated in secure containment.
“you just need to make sure that they're in a cage basically.”
Open the episode · What the OpenAI-Hugging Face Hack Really Tells Us About AI DangerListen at 1:01:56
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.