Nathan Helm-Burger

Featured in:

Articles

Proactive 'If-Then' Safety Cases — LessWrong

Nov 18, 2024 | lesswrong.com | Nathan Helm-Burger

Holden proposed the idea of if-then planning for AI safety. I think this is potentially a very good idea, depending on the implementation details. I've heard criticisms of the If-Then style of planning that it is inherently reactive, rather than proactive. I think this is not necessarily true, and want to make a case for the value of proactive if-then planning. ReactiveFirst, let's look at reactive if-then planning.
Feedback request: what am I missing? — LessWrong

Nov 2, 2024 | lesswrong.com | Nathan Helm-Burger

In the past 3 and a bit years since I left my successful career as a data scientist and machine learning engineer, I've been applying to various AI alignment/safety positions and getting turned down. Job application rejections generally don't give any feedback, so I'm left rather in the dark about what the reasons might be. I was a highly competent and valuable employee at my previous jobs, and my managers and the C-suite of those companies would happily confirm this if asked.
A path to human autonomy — LessWrong

Oct 28, 2024 | lesswrong.com | Nathan Helm-Burger

"Each one of us, and also us as the current implementation of humanity are going to be replaced. Persistence in current form is impossible. It's impossible in biology; every species will either die out or it will change and adapt, in which case it is again not the same species.
Overview of strong human intelligence amplification methods — LessWrong

Oct 8, 2024 | lesswrong.com | Peter McCluskey |Nathan Helm-Burger |Roger Dearnaley |Start AtTheEnd

How can we make many humans who are very good at solving difficult problems? Summary (table of made-up numbers)I made up the made-up numbers in this table of made-up numbers; therefore, the numbers in this table of made-up numbers are made-up numbers. Call to actionIf you have a shitload of money, there are some projects you can give money to that would make supergenius humans on demand happen faster.
My hopes for YouCongress.com — LessWrong

Sep 21, 2024 | lesswrong.com | Nathan Helm-Burger |Hector Perez Arenas

BackgroundFor background on YouCongress.com see this post by Hector Perez Arenas. I love this general concept, and have a lot of ideas for how this implementation could be expanded. I'm hoping that writing out some of my ideas might inspire someone to jump in an contribute code. I would myself if I didn't feel full to the brim on trying to work on AI alignment / control / safety ideas.
GPT-o1 - LessWrong

Sep 16, 2024 | lesswrong.com | Nathan Helm-Burger |Shankar Sivarajan |Rana Dexsin

Deceptive alignment. GPT-4o1 engaged in deception towards developers in order to get deployed, pretending to be aligned in ways it was not. Lying to the developers. It strategically manipulated task data. To be clear, it did not do anything of the sort to its actual developers/testers. What it did was deceive some (non-interactive) roleplay characters, who were labeled "developers" in the roleplay scenario.
Avoiding the Bog of Moral Hazard for AI — LessWrong

Sep 13, 2024 | lesswrong.com | Nathan Helm-Burger

Imagine if you will, a map of a landscape. On this map, I will draw some vague regions. Their boundaries are uncertain, for it is a new and under-explored land. This map is drawn as a graph, but I want to emphasize that the regions are vague guesses, and the true borders could be very convoluted. So here's the problem. We're making these digital minds, these entities which are clearly not human and process the world in different ways from human minds.
Finding Deception in Language Models — LessWrong

Aug 20, 2024 | lesswrong.com | Fedor Ryzhenkov |Nathan Helm-Burger |Philipp Alexander Kreer |Prithviraj Singh Shahani

This June, Apart Research and Apollo Research joined forces to host the Deception Detection Hackathon. Bringing together students, researchers, and engineers from around the world to tackle a pressing challenge in AI safety; preventing AI from deceiving humans and overseers. The hackathon took place both online and in multiple physical locations simultaneously.
Diffusion Guided NLP: better steering, mostly a good thing — LessWrong

Aug 10, 2024 | lesswrong.com | Nathan Helm-Burger

This is a linkpost for https://arxiv.org/html/2408.04220v1
Imbue (Generally Intelligent) continue to make progress — LessWrong

Jun 26, 2024 | lesswrong.com | Nathan Helm-Burger

I've been following the company Imbue and their podcast Generally Intelligent since they started. They've said thoughtful and creative things in their podcast, and I think they are making impressive progress towards AGI considering their relatively smaller size. Just wanting to keep people appraised. If they did hit on something unusually potent, would they get acquired by a larger actor? Hard to know. What is it that they're releasing? In addition to their 70B param model...