enterthewoods

LESSWRONG
LW

enterthewoods — LessWrong

19d

This is a special post for quick takes (aka "shortform"). Only the owner can create top-level comments.

When you improve the capabilities of an LLM (or any AI agent with enough generality really) you also probably improve its ability to cooperate with copies of itself, where cooperation ability is some loose collection of abilities such as checking other copies work, planning work for other copies to carry out, course correcting other copies when they get sidetracked, integrating a copy’s work into the main project, etc.

Now that LLMs are good enough to create useful multi-agent systems such as Claude Code, Cursor, Gas Town, etc., I expect these systems to get better at a faster rate than the underlying models (and not because the people are putting work into improving the structure... (read more)

Replying toAI Futures Timelines and Takeoff Model: Dec 2025 Update

enterthewoods1mo

AI Futures Timelines and Takeoff Model: Dec 2025 Update

Thanks for the reply!

I'm not sure I exactly understand your point.

It is a very confusing point and I didn't explain it well, sorry. I also might just be fundamentally confused and wrong. Hopefully this comment can explain it well enough so you can either shoot it down as incorrect or accept it.

First of all, it might be easier to understand if we replace "effective compute" with "general capabilities" in my original comment. Effective compute causally affects capabilities which causally affects both the METR time horizon measurement and the AI R&D speedup variable. So we can screen off the effective compute node and replace it with a general capabilities node.

If a model has

... (read 450 more words →)

Replying toAI Futures Timelines and Takeoff Model: Dec 2025 Update

enterthewoods1mo

AI Futures Timelines and Takeoff Model: Dec 2025 Update

(Apologies for the long comment).

I want to make a point about your arguments about the growth of time horizons being superexponential. I think they are generally correct, but I think they need to be downweighted somewhat in the timeline model.

This is how I understand your model:

Our starting point is to take the METR graph and extrapolate it exponentially, as they do, making a guess about what agentic coding time horizon would correspond to the AC milestone.

And then you include adjustments to this extrapolation, some of which are arguments about superexponential growth that don't have anything to do with AI R&D speedups feeding back into themselves. Because you are using a threshold on... (read 467 more words →)

Replying toYou will be OK

enterthewoods1mo

You will be OK

2. A working hypothesis: I propose that even though there are multiple possible outcomes, including ones where you, I, and everyone, will very much not be OK, people should live their day to day under the hypothesis they will be OK. Not just because I think that is the most likely outcome, but also because, as I said, it is best not to dwell on the parts of the probability space that are outside your control. This was true for most people during the cold war regarding the possibility of a total nuclear war, and is true now.

I think I disagree slightly with this idea. It feels like a local optimum to... (read more)

An intuitive explanation of backdoor paths using DAGs

enterthewoods

2mo

Crosspost

Epistemic Status: Entirely ripped from Chapter 3 of “Causal Inference: The Mixtape” by Scott Cunningham which is graciously provided for free here and is generally a very good textbook. I hope that by writing this I provide a slightly shorter and easier to read explanation of the highlight (imo) of this chapter. All mistakes are my own and not the textbook’s.

I. Simple DAG

Today I woke up and decided I wanted to explain backdoor paths in an intuitive way both to improve my own understanding and because I think it's a useful idea for rationalists working with causation (which is everyone all the time?). Also I find it really interesting, especially the second... (read 1587 more words →)

Replying toParanoia: A Beginner's Guide

enterthewoods3mo

Paranoia: A Beginner's Guide

Great post - enjoyable read and connected some concepts I hadn't considered together before.

The first thing that immediately comes to mind when I think about how to act in such an environment is reputation: trying to determine which actors are adversarial based on my (or other's) previous interactions with them. I think I would try this before resorting to the other three tactics.

For example, before online ratings became a thing, chain restaurants had one significant advantage over local restaurants: if you were driving through and needed a place to stop and eat, the chain may have an expected quality that is worse than the local restaurant, but at least you knew you... (read more)

Pause from Behind / Losing Heroically

enterthewoods

3mo

Epistemic Status: I think this argument is robust as long as “the conditions” are true. However, I may have miscalculated and left out a condition. I may also be missing something else entirely. Feedback on the post would be helpful in either case.

Introduction

If you want to survive, pause from behind. This can also be described as “Losing Heroically”.

Imagine a simplified model of a race to ASI between two actors. The two actors can each choose to continue racing ahead, or pause and obtain some X percentage-point reduction of takeover risk. Assume that once the actor in front crosses some finish line, they either achieve complete control over the world, or their ASI... (read 1261 more words →)

LESSWRONG
LW

LESSWRONG
LW

enterthewoods

enterthewoods

enterthewoods's Shortform

An intuitive explanation of backdoor paths using DAGs

Pause from Behind / Losing Heroically

enterthewoods

enterthewoods

enterthewoods

enterthewoods's Shortform

An intuitive explanation of backdoor paths using DAGs

Pause from Behind / Losing Heroically