LessWrong (Curated & Popular)

Latest Episodes:

"Comparing Anthropic's Dictionary Learning to Ours" by Robert_AIZI Oct 14, 2023

Show notes

Readers may have noticed many similarities between Anthropic's recent publication Towards Monosemanticity: Decomposing Language Models With Dictionary Learning (LW post) and my team's recent publication Sparse Autoencoders Find Highly Interpretable Directions in Language Models (LW post). Here I want to compare our techniques and highlight what we did similarly or differently. My hope in writing this is to help readers understand the similarities and differences, and perhaps to lay the groundwork for a future synthesis approach.

First, let me note that we arrived at similar techniques in similar ways: both Anthropic and my team follow the lead of Lee Sharkey, Dan Braun, and beren's [Interim research report] Taking features out of superposition with sparse autoencoders, though I don't know how directly Anthropic was inspired by that post. I believe both our teams were pleasantly surprised to find out the other one was working on similar lines, serving as a form of replication.

Some disclaimers: This list may be incomplete. I didn't give Anthropic a chance to give feedback on this, so I may have misrepresented some of their work, including by omission. Any mistakes are my own fault.
Source:
https://www.lesswrong.com/posts/F4iogK5xdNd7jDNyw/comparing-anthropic-s-dictionary-learning-to-ours
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Announcing MIRI’s new CEO and leadership team" by Gretta Duleba Oct 14, 2023

Show notes

In 2023, MIRI has shifted focus in the direction of broad public communication—see, for example, our recent TED talk, our piece in TIME magazine “Pausing AI Developments Isn’t Enough. We Need to Shut it All Down”, and our appearances on various podcasts. While we’re continuing to support various technical research programs at MIRI, this is no longer our top priority, at least for the foreseeable future.

Coinciding with this shift in focus, there have also been many organizational changes at MIRI over the last several months, and we are somewhat overdue to announce them in public. The big changes are as follows.
Source:
https://www.lesswrong.com/posts/NjtHt55nFbw3gehzY/announcing-miri-s-new-ceo-and-leadership-team
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Cohabitive Games so Far" by mako yass Oct 14, 2023

Show notes

A cohabitive game[1] is a partially cooperative, partially competitive multiplayer game that provides an anarchic dojo for development in applied cooperative bargaining, or negotiation.

Applied cooperative bargaining isn't currently taught, despite being an infrastructural literacy for peace, trade, democracy or any other form of pluralism. We suffer for that. There are many good board games that come close to meeting the criteria of a cohabitive game today, but they all[2] miss in one way or another, forbidding sophisticated negotiation from being practiced.

So, over the past couple of years, we've been gradually and irregularly designing and playtesting the first[2] cohabitive boardgame, which for now we can call Difference and Peace Peacewager 1, or P1. This article explains why we think this new genre is important, how it's been going, what we've learned, and where we should go next.
I hope that cohabitive games will aid both laypeople and theorists in developing cooperative bargaining as theory, practice and culture, but I also expect these games to just be more fun than purely cooperative or purely competitive games, supporting livelier dialog, and a wider variety of interesting strategic relationships and dynamics.
Source:
https://www.lesswrong.com/posts/bF353RHmuzFQcsokF/peacewagers-cohabitive-games-so-far
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓
[Curated Post] ✓

"Announcing Dialogues" by Ben Pace Oct 09, 2023

Show notes

As of today, everyone is able to create a new type of content on LessWrong: Dialogues.

In contrast with posts, which are for monologues, and comment sections, which are spaces for everyone to talk to everyone, a dialogue is a space for a few invited people to speak with each other.

I'm personally very excited about this as a way for people to produce lots of in-depth explanations of their world-models in public.

I think dialogues enable this in a way that feels easier — instead of writing an explanation for anyone who reads, you're communicating with the particular person you're talking with — and giving the readers a lot of rich nuance I normally only find when I overhear people talk in person.

In the rest of this post I'll explain the feature, and then encourage you to find a partner in the comments to try it out with.
Source:
https://www.lesswrong.com/posts/kQuSZG8ibfW6fJYmo/announcing-dialogues-1
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Response to Quintin Pope’s Evolution Provides No Evidence For the Sharp Left Turn" by Zvi Oct 09, 2023

Show notes

Response to: Evolution Provides No Evidence For the Sharp Left Turn, due to it winning first prize in The Open Philanthropy Worldviews contest.

Quintin’s post is an argument about a key historical reference class and what it tells us about AI. Instead of arguing that the reference makes his point, he is instead arguing that it doesn’t make anyone’s point - that we understand the reasons for humanity’s sudden growth in capabilities. He says this jump was caused by gaining access to cultural transmission which allowed partial preservation of in-lifetime learning across generations, which was a vast efficiency gain that fully explains the orders of magnitude jump in the expansion of human capabilities. Since AIs already preserve their metaphorical in-lifetime learning across their metaphorical generations, he argues, this does not apply to AI.
Source:
https://www.lesswrong.com/posts/Wr7N9ji36EvvvrqJK/response-to-quintin-pope-s-evolution-provides-no-evidence
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Evaluating the historical value misspecification argument" by Matthew Barnett Oct 09, 2023

Show notes

ETA: I'm not saying that MIRI thought AIs wouldn't understand human values. If there's only one thing you take away from this post, please don't take away that.

Recently, many people have talked about whether some of the main MIRI people (Eliezer Yudkowsky, Nate Soares, and Rob Bensinger[1]) should update on whether value alignment is easier than they thought given that GPT-4 seems to follow human directions and act within moral constraints pretty well (here are two specific examples of people talking about this: 1, 2). Because these conversations are often hard to follow without much context, I'll just provide a brief caricature of how I think this argument has gone in the places I've seen it, which admittedly could be unfair to MIRI[2]. Then I'll offer my opinion that, overall, I think MIRI people should probably update in the direction of alignment being easier than they thought in light of this information, despite their objections.

Note: I encourage you to read this post carefully to understand my thesis. This topic can be confusing, and there are many ways to misread what I'm saying. Also, make sure to read the footnotes if you're skeptical of some of my claims.
Source:
https://www.lesswrong.com/posts/i5kijcjFJD6bn7dwq/evaluating-the-historical-value-misspecification-argument
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Towards Monosemanticity: Decomposing Language Models With Dictionary Learning" by Zac Hatfield-Dodds Oct 09, 2023

Show notes

Neural networks are trained on data, not programmed to follow rules. We understand the math of the trained network exactly – each neuron in a neural network performs simple arithmetic – but we don't understand why those mathematical operations result in the behaviors we see. This makes it hard to diagnose failure modes, hard to know how to fix them, and hard to certify that a model is truly safe.
Luckily for those of us trying to understand artificial neural networks, we can simultaneously record the activation of every neuron in the network, intervene by silencing or stimulating them, and test the network's response to any possible input.
This is a linkpost for https://transformer-circuits.pub/2023/monosemantic-features/
Text of post based on our blog post as a linkpost for the full paper which is considerably longer and more detailed.
Source:
https://www.lesswrong.com/posts/TDqvQFks6TWutJEKu/towards-monosemanticity-decomposing-language-models-with
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"Thomas Kwa's MIRI research experience" by Thomas Kwa and others Oct 05, 2023

Show notes

Moderator note: the following is a dialogue using LessWrong’s new dialogue feature. The exchange is not completed: new replies might be added continuously, the way a comment thread might work. If you’d also be excited about finding an interlocutor to debate, dialogue, or getting interviewed by: fill in this dialogue matchmaking form.

Hi Thomas, I'm quite curious to hear about your research experience working with MIRI. To get us started: When were you at MIRI? Who did you work with? And what problem were you working on?
Source:
https://www.lesswrong.com/posts/qbcuk8WwFnTZcXTd6/thomas-kwa-s-miri-research-experience
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓
[Curated Post] ✓

"'Diamondoid bacteria' nanobots: deadly threat or dead-end? A nanotech investigation" by titotal Oct 02, 2023

Show notes

A lot of people are highly concerned that a malevolent AI or insane human will, in the near future, set out to destroy humanity. If such an entity wanted to be absolutely sure they would succeed, what method would they use? Nuclear war? Pandemics?

According to some in the x-risk community, the answer is this: The AI will invent molecular nanotechnology, and then kill us all with diamondoid bacteria nanobots.
Source:
https://www.lesswrong.com/posts/bc8Ssx5ys6zqu3eq9/diamondoid-bacteria-nanobots-deadly-threat-or-dead-end-a
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

"The Lighthaven Campus is open for bookings" by Habryka Oct 02, 2023

Show notes

Lightcone Infrastructure (the organization that grew from and houses the LessWrong team) has just finished renovating a 7-building physical campus that we hope to use to make the future of humanity go better than it would otherwise.

We're hereby announcing that it is generally available for bookings. We offer preferential pricing for projects we think are good for the world, but to cover operating costs, we're renting out space to a wide variety of people/projects.
Source:
https://www.lesswrong.com/posts/memqyjNCpeDrveayx/the-lighthaven-campus-is-open-for-bookings
Narrated for LessWrong by TYPE III AUDIO.
Share feedback on this narration.
[125+ Karma Post] ✓

Our TOPPODCAST Picks

Follow Us

Stay Connected

LessWrong (Curated & Popular)

Related Podcasts

Links

Stay Connected