Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Adam Newgas
Do you have any ideas?
The Machine Stops (E M Forster, 1909) is an enormously prescient sci-fi dystopia. Everyone lives in isolation, with the titular Machine responsible providing for all their needs, and communication done via video calls. It’s incredibly accurate for predicting some aspects like the internet, social media and AI. But other aspects, like humanity’s total surrender of control to the Machine, have yet to come to pass. But one aspect that always fascinated seems to be on the verge of becoming true.
London Rationalish meetup - Lincoln's Inn Fields
This month, assuming the weather is nice, we'll be in Lincoln's Inn Fields. Most likely the North East quadrant. If it's not nice we'll go to a nearby pub. Our reading list for this month is: 1. Paranoia: A Beginner's Guide 2. In My Misanthropy Era We'll be showing up from 2, and start to discuss these around 3. If you have articles you want to suggest for future readings, you can do that at https://redd.it/v3646u.
The Culture Novels as a Dystopia — LessWrong
I'd mentioned the Golden Age novels by Wright before when we'd gone hiking together, so I thought it'd be worth looking at some related flaws in his utopia. The Sophotechs (the trilogy's equivalent of the minds), are philosophically libertarian. While they do intervene to stop direct violence, they otherwise enforce a system of complete freedom over the self, as well as the maintenance of property rights.
Adam Newgas's Shortform — LessWrong
This is a special post for quick takes by. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page
The Base Model Lens — LessWrong
Many of the stupid errors that LLMs make are attributable to behaviours they learn in during pre-training, then fail to forget or suppress later. This post is here as your reminder that base model behaviour often shows through, and should be one of your foremost theories when trying to explain perplexing LLM results.
Claude is a Ravenclaw — LessWrong
I'm in the midst of doing the MATS program which has kept me super busy, but that didn't stop me working on resolving the most important question of our time: What Hogwarts House does your chatbot belong to? Basically, I submitted each chatbot to the quiz at https://harrypotterhousequiz.org and totted up the results using the inspect framework. I sampled each question 20 times, and simulated the chances of each house getting the highest score.
My Failed AI Safety Research Projects (Q1/Q2 2025) — LessWrong
This year I've been on sabbatical, and have spent my time upskilling in AI Safety. Part of that is doing independent research projects in different fields. Some of those items have resulted in useful output, notably A Toy Model of the U-AND Problem, Do No Harm? and SAEs and their Variants. And then there are others that I've just failed fast, and moved on. Here I write up those projects that still have something to say, even if it's mostly negative results.
A Technique of Pure Reason — LessWrong
Looking a little ahead into the future, I think LLMs are going to stop being focused on knowledgeable, articulate chatbots, but instead be more efficient models that are weaker in these areas than current models, but relatively stronger at reasoning, a pure-reasoner model. The rest will be bolted on via tool-use and other scaffolding. Chatbots make a great replacement for Google searches because they know a lot about everything. But that knowledge comes at a price.
An Introduction to SAEs and their Variants for Mech Interp — LessWrong
I aim to cover a lot of ground, but only briefly. Click through the links for more detailed explanations. Several of the techniques here see general use outside of interpretability. My definitions/references lean towards how they specifically apply to Mechanistic Interpretability Sparse Dictionary Learning describes any ML technique that aims to find a set of “atoms” that can be sparsely combined to represent a dataset.
Computational Superposition in a Toy Model of the U-AND Problem — LessWrong
Thanks to @Linda Linsefors and @Kola Ayonrinde for reviewing the draft. I built a toy model of the Universal-AND Problem described in Toward A Mathematical Framework for Computation in Superposition (CiS). It successfully learnt a solution to the problem, providing evidence that such computational superposition can occur in the wild. In this post, I'll describe the circuits I've found that model learns to use, and explain why they work.
Do No Harm? Navigating and Nudging AI Moral Choices — LessWrong
TL;DR: How do AI systems make moral decisions, and can we influence their ethical judgments? We probe these questions by examining Llama's 70B (3.1 and 3.3) responses to moral dilemmas, using Goodfire API to steer its decision-making process. Our experiments reveal that simply reframing ethical questions - from "harm one to save many" to "let many perish to avoid harming one" - dramatically affects both the model's responses and its susceptibility to steering.
An Uncanny Moat - LessWrong
Back in the early days of computer animation, the technology at the time really struggled with realism. The first cartoons were necessarily abstract, or cartoony. As time progressed, the technology caught up. CGI now can be all but indistinguishable from real life. But there was a brief period, as seen in films like The Polar Express or Final Fantasy: The Spirits Within, when the artists aimed for realism and didn’t quite get there. These films were often critically panned.
London Rationalish Meetup — LessWrong
Our reading list this month is: 1. What should you change in response to an "emergency"? And AI risk (https://www.lesswrong.com/posts/mmHctwkKjpvaQdC3c/what-should-you-change-in-response-to-an-emergency-and-ai) 2. In Partial, Grudging Defense Of The Hearing Voices Movement (https://www.astralcodexten.com/p/in-partial-grudging-defense-of-the) We'll start to discuss these around 3. If you have articles you want to suggest for future readings, you can do that at https://redd.it/v3646u.
London Rationalish Meetup — LessWrong
Phil is out this month, so I'm hosting instead. We're going to take a chance on the weather, and try a picnic in Lincoln's Inn Field. Look for a group in the north east quadrant with a green picnic blanket. We'll move to the Shakespear's Head if the weather is poor. Our reading list is: 1. Rich Friend, Poor Friend (https://jenn.site/2022/08/rich-friend-poor-friend/) 2. Once we can see them, it's too late (https://scottaaronson.blog/?p=5253) We'll start to discuss these around 3.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Adam
Contact Adam, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack