To your question, I am not a bot, my LinkedIn is in my profile if you want to know who I am.

I'm persisting because, I guess, I'm really confused by your own insistence, and feel curious to get to the bottom of the weird misunderstanding we must be having (maybe you're trying to argue something different than "user chmod775 intended to refer to 'ablation' and was mistaken to write 'Just put "uncensored", "abliterated", or "heretic" into search on huggingface/ollama/etc and pick any them' instead of 'Just put "uncensored", "ablated", or "heretic" into search on huggingface/ollama/etc and pick any them'?). And I have a lot of free time on a climbing vacation where my brain is too mushy to do anything more productive than talk to people on the interblags.

The wiki "ablation" article you yourself linked dedicates a section to explain "abliteration".

Googling abliteration arxiv yields at least one page of papers that mention it in the abstract (all but one in the title too). I counted 9 unique papers.

If it was shown that all of these were posted after this discussion started, or by people related to the person you tried to correct, I would be convinced that abliteration is not a real word. But evidence keeps pointing otherwise, nnd you keep arguing with evidence that proves "ablate" is a word (to which we all agree), not evedence that proves "abliterate" isn't.

You did show evidence that it's a pretty new word (of course it is! it's a pretty new technique in a field that didn't exist before the first open source RLHF'd models were released in '23!), and indeed, this (different) wiktionary page contains its origin story from '24: https://en.wiktionary.org/wiki/abliterate#English

Except for the initial comment, they were aggressive and sometimes disrespectful claims that "the word is spelled ablation, here are some papers that use it" in response to people saying "yes, we know what ablation means, but GP is intentionally using a separate word 'abliteration' that is the accepted word for the kind of ablation he's talking about, see links to respectable sources using or defining it". I downvoted them because I feel the discussion would be more valuable and feel nicer to read without them, and you could just read any of the offered links before responding and save the trouble.

But the main loop was to show Fable the solution, ask it for a prompt that would get a clean context Fable to find a solution, run it, if it works ask the first Fable to remove details, if it doesn't quote a status report and ask it where the clean Fable went askew and to edit the prompt to prevent that.

Since none was published, I tried to "clean room reverse engineer" it: give one Claude Fable the result and ask it to generate a writeup of how to arrive at it without any spoilers, then ask a second Fable to follow the write up, if it's too easy remove details, if it's too hard add hints. I could have simplified further, I stopped because it's time to sleep, and I'm sharing because it gave me some intuition for what's going on.

This is what a successful run looks like (sadly Anthropic hide Chains of Thought):

https://claude.ai/share/80526d56-1c23-407d-8f5c-59a704221454

## Intuition

This is my understanding of the interesting ideas (probably too summarized for Fable to consistently get it without a good harness; take with a grain of salt, I'm not a mathematician; later there is a full prompt that was tested and contains everything needed):

* No Bass–Connell–Wright or Drużkowski normal forms (those are reparametrizations that feel natural in this search but they turn low-complexity examples into high-complexity by trading off degree vs dimension, and the counterexample is low complexity)

* Look in C^3, not C^2, C^2 is probably not interesting enough

* Look for a 3:1 cover, not 2:1, there's some result due to Euler (as always) that shows 2:1 will not work

* Look for a composition of two functions (a ratio of polynomials and a shear) that have Jacobian determinants `x` and `c/x` everywhere, except at `x=0` (do the standard trick for not defining at a hole and shoving all the problems into that one hole, that's where the `1 + xy` comes from)

## Prompt for reproducing CoT

Here: https://gist.github.com/SonOfLilit/8882a145048ba260b160568ba...

Comments URL: https://news.ycombinator.com/item?id=48986943

Points: 7

# Comments: 2

e.g. "maybe the user's example is DESIGNED to be "correct in the stated facts" &c"

I mean that the "remove a word" 'symbol' is a 'word' that represents the verb he was trying to invoke, by sounding like it.

Birds chirp, bees buzz, moderators, toilets flush.

The amount and level of power use of cryptography primitives and their minutiae is insane. A cryptographic algorithm can usually be described on a post it note. A non-interactive zk commitment scheme would take a 200 page book.

(Though to be seriousit's Cryptography 3: Return of the String, because Cryptography 2 is Public Key Cryptography)

I guess nobody's commenting on this because it's very dense math without any context. Lucky for me I spent an hour or two yesterday learning how practical non-interactive zero knowledge proofs work.

In SNARKs (and other commitment schemes based on polynomials in elliptic curve groups, hope I got the terminology right), you verify the commitment (unneeded technical details: polynomial on EC at secret point nobody knows including the committer so he has to make the polynomial match at most points, and polynomials that match at most points match at all points) by multiplying two things you calculated from the circuit and commitment (which is just a couple of group elements) and verifying that it comes out as 1. The multiplication and comparison under encryption is done with a homomorphic encryption primitive-type thing called a "pairing" (normally with elliptic curve encryption only addition can be done on secret group elements that you don't know the value of).

They found a way to tell a specific library that implements this operation "believe me, this pairing is ok" that doesn't depend on any of those technical things. Just "these are not the droids you're looking for". Because it was not validating that some precomputed thing needed for the pairing verification actually matches this specific situation, and there are trivial parameters that would always yield 1 (but not be valid in the situation).

Every node that uses this library to validate would lose synchronization with every other node (if we take them at their word that it's not a monoculture), the bigger half would be considered "correct" according to how blockchains work, if it's the non-exploitable half - just lots of wasted resources and longer settlement times, if it's the exploitable half - illegal transactions would need to be reverted by agreement of the community, which is some sort of reset.

Within Unicode is defined a DSL used internally by the library implementers to define some business logic, like most DSLs it is turing complete. Anyone with the ability to make you run their rules file already has the ability to make you run arbitrary code (it's a software vendor for software you use).

It's still always fun to find Weird Machines, but as they go, this one is not very weird (it's one of the known families of programming languages, the Mathematica language being the most well known example. The person who specified this most likely was aware that this is turing complete and it's the rules author's responsibility not to write infinite loops).

So... of course these questions are addressed in the 38 page essay that introduced the idea.

Specifically, it's not "calling it coherent", it's "assigning more importance to the parts that cohere than the parts that diverge" as one of the core principles (it's one philosopher's opinion, others disagree), with a lot of specific guidelines about how to prefer consensus or kicking decisions down the road and how to deal with complications like "what about dolphins" or "what about our great-great-grandchildren who will be as insane in our eyes as we are in the eyes of 17th century westerners, do their 'votes' count too?".

Of course, like any work of philosophy, it presupposes some pretty incredible things (like a Godlike intelligence that can be made to care deeply about following the spirit of this framework). But you could write a worse first draft for "what would we want AI to be aligned to, if we could define to our heart's content?"

https://intelligence.org/files/CEV.pdf

"How can we even define what an aligned AI should do, if human's are not aligned with each other?" as well as "What does being aligned mean when you're a wizard box who's main influence on the world is to create stronger wizard boxes?" and other deep philosophical questions.

They came up with a framework called Coherent Extrapolated Volition to address this specific question. https://en.wikipedia.org/wiki/Coherent_extrapolated_volition

Probably many noticed and nobody wanted to spam with the complaint, I decided the spam is worth it for the author to get some feedback.