You may have already seen this, but in case you hadn't already, a related CFAR technique is internal double crux: https://www.lesswrong.com/tag/internal-double-crux
This would benefit from an example. I think this technique has a lot of potential for use with LLMs, and an example would make it a great supplement to a Claude Project's knowledge base.
I provided one here!
Totally agree about LLMs. I've recently been finding giving o3 Deep Research this prompt to be super helpful:
"X=[thing I want to research]
Do a deep dive into X. Tell me the steelman arguments in favor of X.
Then tell me the steelman counter-arguments to X.
Then tell me the steelman counter-counter-arguments to X.
Then tell me the steelman counter-counter-counter-arguments to X
Make sure to link to primary sources and the full thing that happened, to avoid things being quoted out of context"
It's been particularly helpful for investigating anything political.
This reminds me of the kind of min-maxing good chess players tend to do when coming up with moves. They come up with a few good moves, then consider the strongest responses the opponent could make, branching out into a tree. To keep the size of the tree manageable, they only consider the best moves they can think of. A common beginner mistake is to play a move that looks good, as long as you assume the opponent "plays along". (Like, threaten a piece and then assume the opponent won't do anything to remove the threat.) I think this could be called strawmanning your opponent. If you steelman your opponent, you tend to play better, because your beliefs about the effectiveness of your moves will be more accurate. But you should of course also be sharpening your beliefs about which moves the opponent is likely to make, which involves thinking about your possible responses, etc.
This is an old post of mine from The Nonlinear blog that I thought really belonged on LessWrong.
I have a tool for thinking that I call “steelman solitaire”. I have found that it comes to much better conclusions than doing “free-style” thinking, so I thought I should share it with more people.
In summary, it consists of arguing with yourself in the program Workflowy or Roam, alternating between writing a steelman of an argument, a steelman of a counter-argument, a steelman of a counter-counter-argument, etc.
In this blog post I’ll first explain the broad steps, then list the benefits, and finally, go into more depth on how to do it.
Strawmanning means presenting the opposing view in the least charitable light – often so uncharitably that it does not resemble the view that the other side actually holds. The term of steelmanning was invented as a counter to this; it means taking the opposing view and trying to present it in its strongest form. This has sometimes been criticized because often the alternative belief proposed by a steelman also isn’t what the other people actually believe. For example, there’s a steelman argument that states that the reason organic food is good is that monopolies are generally bad and Monsanto having a monopoly on food could lead to disastrous consequences. This might indeed be a belief held by some people who are pro-organic, but a huge percentage of people are just falling prey to the naturalistic fallacy.
While steelmanning may not be perfect for understanding people’s true reasons for believing propositions, it is very good for coming to more accurate beliefs yourself. If the reason you believe you don’t have to care about buying organic is that you believe that people only buy organic because of the naturalistic fallacy, you might be missing out on the fact that there’s a good reason for you to buy organic because you think monopolies on food are dangerous.
However – and this is where steelmanning back and forth comes in – what if buying organic doesn’t necessarily lead to breaking the monopoly? Maybe upon further investigation, Monsanto doesn’t have a monopoly. Or maybe multiple organizations have copyrighted different gene edits, so there’s no true monopoly.
The idea behind steelman solitaire is to not stop at steelmanning the opposing view. It’s to steelman the counter-counter-argument as well. As has been said by more eloquent people than myself, you can’t consider an argument and counter-argument and consider yourself a virtuous rationalist. There are very long chains of counter^x arguments, and you want to consider the steelman of each of them. Don’t pick any side in advance. Just commit to trying to find the true answer.
This is all well and good in principle but can be challenging to keep organized. This is where Workflowy or Roam comes in. Workflowy allows you to have counter-arguments nested under arguments, counter-counter-arguments nested under counter-arguments, and so forth. That way you can zoom in and out and focus on one particular line of reasoning, realize you’ve gone so deep you’ve lost the forest for the trees, zoom out, and realize what triggered the consideration in the first place. It also allows you to quickly look at the main arguments for and against. Here’s a worked example for a question.
That’s the broad-strokes explanation of the method. Below, I’ll list a few pointers that I follow, though please do experiment and tweak. This is by no means a final product.
In summary, steelman solitaire means steelmanning arguments back and forth repeatedly. It helps with:
The method to follow is to make a claim, make a steelman against that claim, then a steelman against that claim, and on and on until you can’t anymore or are convinced one way or the other.
Acknowledgements: I’d like to thank Spencer Greenberg for both inspiring the original idea with Clearer Thinking’s Belief Challenger tool and for coming up with a much better name for the concept than my original “steelmanning back and forth”.