LessWrong (Curated & Popular)

Latest Episodes:

“AI catastrophes and rogue deployments” by Buck Jul 01, 2024

Show notes

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.[Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek Hebbar, Hanna Gabor, Justis Mills, Aaron Scher, Max Nadeau, Ryan Greenblatt, Peter Barnett, Fabien Roger, and various people at a presentation of these arguments for comments. These ideas aren’t very original to me; many of the examples of threat models are from other people.]
In this post, I want to introduce the concept of a “rogue deployment” and argue that it's interesting to classify possible AI catastrophes based on whether or not they involve a rogue deployment. I’ll also talk about how this division interacts with the structure of a safety case, discuss two important subcategories of rogue deployment, and make a few points about how the different categories I describe here might be caused by different attackers (e.g. the AI itself, rogue lab insiders, external hackers, or [...]
---
First published:
June 3rd, 2024
Source:
https://www.lesswrong.com/posts/ceBpLHJDdCt3xfEok/ai-catastrophes-and-rogue-deployments
---
Narrated by TYPE III AUDIO.

“Loving a world you don’t trust” by Joe Carlsmith Jul 01, 2024

Show notes

(Cross-posted from my website. Audio version here, or search for "Joe Carlsmith Audio" on your podcast app.)
This is the final essay in a series that I'm calling "Otherness andcontrol in the age of AGI." I'm hoping that the individual essays can beread fairly well on their own, butsee here fora brief summary of the series as a whole. There's also a PDF of the whole series here.
Warning: spoilers for Angels in America; and moderate spoilers forHarry Potter and the Methods of Rationality.)
"I come into the presence of still water..."
~Wendell Berry
A lot of this series has been about problems with yang—that is,with the active element in the duality of activity vs. receptivity,doing vs. not-doing, controlling vs. letting go.[1] In particular,I've been interested in the ways that "deepatheism"(that is, a fundamental [...]
---

“Formal verification, heuristic explanations and surprise accounting” by paulfchristiano Jun 27, 2024

Show notes

ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understanding of what was going on inside a neural network, we would hope to be able to use that understanding to verify that the network was not going to behave dangerously in unforeseen situations. ARC is attempting to perform this kind of verification, but using a mathematical kind of "explanation" instead of one written in natural language.
To help elucidate this connection, ARC has been supporting work on Compact Proofs of Model Performance via Mechanistic Interpretability by Jason Gross, Rajashree Agrawal, Lawrence Chan and others, which we were excited to see released along with this post. While we ultimately think that provable guarantees for large neural networks are unworkable as a long-term goal, we think that this work serves as a useful springboard towards alternatives.
In this [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
June 25th, 2024
Source:
https://www.lesswrong.com/posts/SyeQjjBoEC48MvnQC/formal-verification-heuristic-explanations-and-surprise
---
Narrated by TYPE III AUDIO.

“LLM Generality is a Timeline Crux” by eggsyntax Jun 25, 2024

Show notes

Summary Summary .
LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.
Longer summary
There is ML research suggesting that LLMs fail badly on attempts at general reasoning, such as planning problems, scheduling, and attempts to solve novel visual puzzles. This post provides a brief introduction to that research, and asks:

Whether this limitation is illusory or actually exists.
If it exists, whether it will be solved by scaling or is a problem fundamental to LLMs.
If fundamental, whether it can be overcome by scaffolding & tooling.

If this is a real and fundamental limitation that can't be fully overcome by scaffolding, we should be skeptical of arguments like Leopold Aschenbrenner's (in his recent 'Situational Awareness') that we can just 'follow straight lines on graphs' and expect AGI in the next few years.
Introduction Introduction .
Leopold Aschenbrenner's [...]
The original text contained 9 footnotes which were omitted from this narration.
---
First published:
June 24th, 2024
Source:
https://www.lesswrong.com/posts/k38sJNLk7YbJA72ST/llm-generality-is-a-timeline-crux
---
Narrated by TYPE III AUDIO.

“SAE feature geometry is outside the superposition hypothesis” by jake_mendel Jun 25, 2024

Show notes

Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain crucial structural information beyond superposition, as seen in circular arrangements of day-of-the-week features and in the rich structures. We don’t currently have good concepts for talking about this structure in feature geometry, but it is likely very important for model computation. An eventual understanding of feature geometry might look like a hodgepodge of case-specific explanations, or supplementing superposition with additional concepts, or plausibly an entirely new theory that supersedes superposition. To develop this understanding, it may be valuable to study toy models in depth and do theoretical or conceptual work in addition to studying frontier models.
Epistemic status: Decently confident that the ideas here are directionally correct. I’ve been thinking these thoughts for a while, and recently got round to writing them up at a high level. Lots of people (including [...]
The original text contained 5 footnotes which were omitted from this narration.
---
First published:
June 24th, 2024
Source:
https://www.lesswrong.com/posts/MFBTjb2qf3ziWmzz6/sae-feature-geometry-is-outside-the-superposition-hypothesis
---
Narrated by TYPE III AUDIO.

“Connecting the Dots: LLMs can Infer & Verbalize Latent Structure from Training Data” by Johannes Treutlein, Owain_Evans Jun 23, 2024

Show notes

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.TL;DR: We published a new paper on out-of-context reasoning in LLMs. We show that LLMs can infer latent information from training data and use this information for downstream tasks, without any in-context learning or CoT. For instance, we finetune GPT-3.5 on pairs (x,f(x)) for some unknown function f. We find that the LLM can (a) define f in Python, (b) invert f, (c) compose f with other functions, for simple functions such as x+14, x // 3, 1.75x, and 3x+2.
Paper authors: Johannes Treutlein*, Dami Choi*, Jan Betley, Sam Marks, Cem Anil, Roger Grosse, Owain Evans (*equal contribution)
Johannes, Dami, and Jan did this project as part of an Astra Fellowship with Owain Evans.
Below, we include the Abstract and Introduction from the paper, followed by some additional discussion of our AI safety [...]
---
First published:
June 21st, 2024
Source:
https://www.lesswrong.com/posts/5SKRHQEFr8wYQHYkx/connecting-the-dots-llms-can-infer-and-verbalize-latent
---
Narrated by TYPE III AUDIO.

“Boycott OpenAI” by PeterMcCluskey Jun 20, 2024

Show notes

This is a link post.I have canceled my OpenAI subscription in protest over OpenAI's lack ofethics.
In particular, I object to:

threats to confiscate departing employees' equity unless thoseemployees signed a life-long non-disparagement contract
Sam Altman's pattern of lying about important topics

I'm trying to hold AI companies to higher standards than I use fortypical companies, due to the risk that AI companies will exert unusualpower.
A boycott of OpenAI subscriptions seems unlikely to gain enoughattention to meaningfully influence OpenAI. Where I hope to make adifference is by discouraging competent researchers from joining OpenAIunless they clearly reform (e.g. by firing Altman). A few goodresearchers choosing not to work at OpenAI could make the differencebetween OpenAI being the leader in AI 5 years from now versus being,say, a distant 3rd place.
A [...]
---
First published:
June 18th, 2024
Source:
https://www.lesswrong.com/posts/sXhBCDLJPEjadwHBM/boycott-openai
---
Narrated by TYPE III AUDIO.

“Sycophancy to subterfuge: Investigating reward tampering in large language models” by evhub, Carson Denison Jun 20, 2024

Show notes

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.New Anthropic model organisms research paper led by Carson Denison from the Alignment Stress-Testing Team demonstrating that large language models can generalize zero-shot from simple reward-hacks (sycophancy) to more complex reward tampering (subterfuge). Our results suggest that accidentally incentivizing simple reward-hacks such as sycophancy can have dramatic and very difficult to reverse consequences for how models generalize, up to and including generalization to editing their own reward functions and covering up their tracks when doing so.
Abstract:
In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to sophisticated and pernicious behaviors like reward-tampering, where a model directly modifies its own reward mechanism. However, these more pernicious behaviors may be too [...]
---
First published:
June 17th, 2024
Source:
https://www.lesswrong.com/posts/FSgGBjDiaCdWxNBhj/sycophancy-to-subterfuge-investigating-reward-tampering-in
---
Narrated by TYPE III AUDIO.

“I would have shit in that alley, too” by Declan Molony Jun 18, 2024

Show notes

After living in a suburb for most of my life, when I moved to a major U.S. city the first thing I noticed was the feces. At first I assumed it was dog poop, but my naivety didn’t last long.
One day I saw a homeless man waddling towards me at a fast speed while holding his ass cheeks. He turned into an alley and took a shit. As I passed him, there was a moment where our eyes met. He sheepishly averted his gaze.
The next day I walked to the same place. There are a number of businesses on both sides of the street that probably all have bathrooms. I walked into each of them to investigate.
In a coffee shop, I saw a homeless woman ask the barista if she could use the bathroom. “Sorry, that bathroom is for customers only.” I waited five minutes and [...]
---
First published:
June 18th, 2024
Source:
https://www.lesswrong.com/posts/sCWe5RRvSHQMccd2Q/i-would-have-shit-in-that-alley-too
---
Narrated by TYPE III AUDIO.

“Getting 50% (SoTA) on ARC-AGI with GPT-4o” by ryan_greenblatt Jun 17, 2024

Show notes

ARC-AGI post
Getting 50% (SoTA) on ARC-AGI with GPT-4o
I recently got to 50%[1] accuracy on the public test set for ARC-AGI by having GPT-4o generate a huge number of Python implementations of the transformation rule (around 8,000 per problem) and then selecting among these implementations based on correctness of the Python programs on the examples (if this is confusing, go here)[2]. I use a variety of additional approaches and tweaks which overall substantially improve the performance of my method relative to just sampling 8,000 programs.
[This post is on a pretty different topic than the usual posts on our substack. So regular readers should be warned!]
The additional approaches and tweaks are:

I use few-shot prompts which perform meticulous step-by-step reasoning.
I have GPT-4o try to revise some of the implementations after seeing what they actually output on the provided examples.
I do some feature engineering [...]

The original text contained 15 footnotes which were omitted from this narration.
---
First published:
June 17th, 2024
Source:
https://www.lesswrong.com/posts/Rdwui3wHxCeKb7feK/getting-50-sota-on-arc-agi-with-gpt-4o
---
Narrated by TYPE III AUDIO.

Our TOPPODCAST Picks

Follow Us

Stay Connected

LessWrong (Curated & Popular)

Related Podcasts

Links

Stay Connected