This is a special post for quick takes by Raemon. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
This is an experiment in short-form content on LW2.0. I'll be using the comment section of this post as a repository of short, sometimes-half-baked posts that either:
don't feel ready to be written up as a full post
I think the process of writing them up might make them worse (i.e. longer than they need to be)
I ask people not to create top-level comments here, but feel free to reply to comments like you would a FB post.
Reading through Backdoors as an analogy for deceptive alignment prompted me to think about a LW feature I might be interested in. I don't have much math background, and have always found it very effortful to parse math-heavy posts. I expect there are other people in a similar boat.
In modern programming IDEs it's common to have hoverovers for functions and variables, and I think it's sort of crazy that we don't have that for math. So, I'm considering a LessWrong feature that:
takes in a post (i.e. when you save or go to publish a draft)
identifies the LaTeX terms in the post
creates a glossary for what each term means. (This should probably require confirmation by the author)
makes a hoverover for each term so when you mouseover it reminds you.
On "Backdoors", I asked the LessWrong-integrated LLM: "what do the Latex terms here mean"?
It replied :
The LaTeX symbols in this passage represent mathematical notations. Let me explain each of them:
F : This represents a class of functions. The curly F denotes that it's a set or collection of functions.
f∈F : This means that f is a function that belongs to (is an element of) the class F.
f∗ : The asterisk superscript typically denotes a modified or special version of something. Here, it represents the backdoored function.
ε : This Greek letter (epsilon) is often used to denote a small quantity or tolerance.
x∗ : Similar to f∗, this represents a special input, in this case, the backdoor trigger.
These symbols are used to formally describe the game between the attacker and defender:
F is the set of all possible functions the attacker can choose from.
f is the original function chosen by the attacker.
f∗ is the backdoored function created by the attacker.
ε is the tolerance for how similar f and f∗ must be on most inputs.
x∗ is the backdoor trigger input, on which f and f∗ behave differently.
This looks at least pretty close to the intended meaning, but curious if it feels like it's wrong or missing nuance in any places @Jacob_Hilton@Mark Xu. Also curious whether this would be helpful to people.
Other related features that'd be easy to incorporate into this are John's ideas from here:
Imagine a tool in which I write out mathematical equations on the left side, and an AI produces prototypical examples, visuals, or stories on the right, similar to what a human mathematician might do if we were to ask what the mathematician were picturing when looking at the math. (Presumably the interface would need a few iterations to figure out a good way to adjust the AI's visualization to better match the user's.)
I've fantasized about a good version of this feature for math textbooks since college - would be excited to beta test or provide feedback about any such things that get explored! (I have a couple math-heavy posts I'd be down to try annotating in this way.)
This is an experiment in short-form content on LW2.0. I'll be using the comment section of this post as a repository of short, sometimes-half-baked posts that either:
I ask people not to create top-level comments here, but feel free to reply to comments like you would a FB post.