Paul Christiano – We could be 12 months away from AIs that can overthrow the government
Paul Christiano is head of the Alignment Research Center. Previously, he was head of AI safety at the US AI Safety Institute. Before that, he led alignment at OpenAI, where he invented RLHF. He’s recently joined OpenAI’s board (though here he is speaking as a private citizen).
Paul thinks that on the current trajectory (absent any slowing down), there is a 1 in 3 chance that we could have superintelligence powerful enough to overthrow the government within a year. (He articulates a concrete scenario).
He argues that the labs should pause further algorithmic progress until they can secure their weights and research secrets. Otherwise China could simply steal the superintelligence in the middle of the intelligence explosion, and the labs would no longer be able to slow down even if they saw their models going off the rails.
He also explains how AIs will be trained during the intelligence explosion, and why even a system trained entirely inside a data center could still have the capabilities profile such that humans would have very little chance of competing with it or controlling it.
And he discusses the plan for alignment - basically, making a superintelligence that actually does what we ask the way we mean it. Fixing reward hacks and building better graders will help up till the next few model generations, but he thinks that no single current approach has better than even odds of letting us control superintelligence. The hope is that the AIs figure out the solution to this problem during the intelligence explosion.
Watch on YouTube; read the transcript.
Sponsors
* Jane Street has finally come around on formal methods. Ron Minsky, who co-heads Jane Street’s technology group, told me that up until recently, formal methods just weren’t worth the cost. But coding agents have made them easier to apply AND increased the importance of code verification. So now Jane Street is hiring Formal Methods Engineers in both their London and New York offices. If you’re interested, or if you want to watch my full conversation with Ron, go to janestreet.com/dwarkesh
* Antithesis is NOT another LLM-based code-review tool. It doesn’t try to reason abstractly about how a PR might break your system. Instead, it just runs your code. You start by defining the rules that your system must never break. Then, whenever an agent proposes a change, Antithesis runs your code through thousands of adversarial worlds, testing whether or not it still adheres to your rules. If you want to try it, go to antithesis.com/dwarkesh and use code DWARKESH for 50% off your first month.
* WorkOS lets you give agents their own sign-up flow. This matters because agents tend to pick tools they can use right away, rather than ones that require humans to register. Fortunately, providing this kind of dedicated path is easy: if you already use WorkOS for login, you just toggle on “Agent Registration” in the WorkOS dashboard. Once it’s enabled, you can decide what agents are allowed to do on their own, and what needs to wait until the person they’re working for gets involved, all with the permissions you’ve already set up. Learn more at workos.com/authkit
Timestamps
(00:00:00) – We could be 12 months away from AIs that can overthrow the government
(00:11:44) – Why an AI might want to takeover
(00:20:49) – How an AI takeover could happen
(00:35:35) – If labs keep racing without security, China will just steal the weights of superintelligence
(00:53:15) – The case for pausing now instead of later
(00:59:31) – Superintelligence will be good at learning from real-world experience
(01:11:32) – Crossing the sim-to-real gap
(01:22:23) – METR says AI progress doubled, so why is revenue growth slowing?
(01:27:57) – The best plan we have is to build the plane as we fly it
This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.dwarkesh.com
Paul Christiano — Preventing an AI takeover
Paul Christiano is the world’s leading AI safety researcher. My full episode with him is out!
We discuss:
- Does he regret inventing RLHF, and is alignment necessarily dual-use?
- Why he has relatively modest timelines (40% by 2040, 15% by 2030),
- What do we want post-AGI world to look like (do we want to keep gods enslaved forever)?
- Why he’s leading the push to get to labs develop responsible scaling policies, and what it would take to prevent an AI coup or bioweapon,
- His current research into a new proof system, and how this could solve alignment by explaining model's behavior
- and much more.
Watch on YouTube. Listen on Apple Podcasts, Spotify, or any other podcast platform. Read the full transcript here. Follow me on Twitter for updates on future episodes.
Open Philanthropy
Open Philanthropy is currently hiring for twenty-two different roles to reduce catastrophic risks from fast-moving advances in AI and biotechnology, including grantmaking, research, and operations.
For more information and to apply, please see the application: https://www.openphilanthropy.org/research/new-roles-on-our-gcr-team/
The deadline to apply is November 9th; make sure to check out those roles before they close.
Timestamps
(00:00:00) - What do we want post-AGI world to look like?
(00:24:25) - Timelines
(00:45:28) - Evolution vs gradient descent
(00:54:53) - Misalignment and takeover
(01:17:23) - Is alignment dual-use?
(01:31:38) - Responsible scaling policies
(01:58:25) - Paul’s alignment research
(02:35:01) - Will this revolutionize theoretical CS and math?
(02:46:11) - How Paul invented RLHF
(02:55:10) - Disagreements with Carl Shulman
(03:01:53) - Long TSMC but not NVIDIA
Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe
168 - How to Solve AI Alignment with Paul Christiano
Paul Christiano runs the Alignment Research Center, a non-profit research organization whose mission is to align future machine learning systems with human interests. Paul previously ran the language model alignment team at OpenAI, the creators of ChatGPT.
Today, we’re hoping to explore the solution-landscape to the AI Alignment problem, and hoping Paul can guide us on that journey.
------ ✨ DEBRIEF | Unpacking the episode: https://www.bankless.com/debrief-paul-christiano ------ ✨ COLLECTIBLES | Collect this episode: https://collectibles.bankless.com/mint
------ ✨ Always wanted to become a Token Analyst? Bankless Citizens get exclusive access to Token Hub. Join Them. https://bankless.cc/TokenHubRSS
------ In today’s episode, Paul answers many questions, but the overarching ones are: 1) How BIG is the AI Alignment problem? 2) How HARD is the AI Alighment problem? 3) How SOLVABLE is the AI Alignment problem?
Does humanity have a chance? Tune in to hear Paul’s thoughts.
------ BANKLESS SPONSOR TOOLS:
⚖️ ARBITRUM | SCALING ETHEREUM https://bankless.cc/Arbitrum
🐙KRAKEN | MOST-TRUSTED CRYPTO EXCHANGE https://bankless.cc/kraken
🦄UNISWAP | ON-CHAIN MARKETPLACE https://bankless.cc/uniswap
👻 PHANTOM | FRIENDLY MULTICHAIN WALLET https://bankless.cc/phantom-waitlist
🦊METAMASK LEARN | HELPFUL WEB3 RESOURCE https://bankless.cc/MetaMask
------ Topics Covered
0:00 Intro 9:20 Percentage Likelihood of Death by AI 11:24 Timing 19:15 Chimps to Human Jump 21:55 Thoughts on ChatGPT 27:51 LLMs & AGI 32:49 Time to React? 38:29 AI Takeover 41:51 AI Agency 49:35 Loopholes 51:14 Training AIs to Be Honest 58:00 Psychology 59:36 How Solvable Is the AI Alignment Problem? 1:03:48 The Technical Solutions (Scalable Oversight) 1:16:14 Training AIs to be Bad?! 1:18:22 More Solutions 1:21:36 Stabby AIs 1:26:03 Public vs. Private (Lab) AIs 1:28:31 Inside Neural Nets 1:32:11 4th Solution 1:35:00 Manpower & Funding 1:38:15 Pause AI? 1:43:29 Resources & Education on AI Safety 1:46:13 Talent 1:49:00 Paul’s Day Job 1:50:15 Nobel Prize 1:52:35 Treating AIs with Respect 1:53:41 Uptopia Scenario 1:55:50 Closing & Disclaimers
------ Resources:
Alignment Research Center https://www.alignment.org/
Paul Christiano’s Website https://paulfchristiano.com/ai/
----- Not financial or tax advice. This channel is strictly educational and is not investment advice or a solicitation to buy or sell any assets or to make any financial decisions. This video is not tax advice. Talk to your accountant. Do your own research.
Disclosure. From time-to-time I may add links in this newsletter to products I use. I may receive commission if you make a purchase through one of these links. Additionally, the Bankless writers hold crypto assets. See our investment disclosures here: https://www.bankless.com/disclosures