SonOfLilit
Joined 19 years ago
Karma
2,714
Submissions
778
Member since
Oct 6
Recent submissions
Comment · 7 days ago
Absolutely insane.
If anyone's curious, the handwritten Go bot is very weak, about the level of a human complete beginner. An MLP is a very very bad architecture for a Go network, it's amazing that it does anything at all, but it's one of the least impressive results in the paper.
Play it here, "best move" is a bit stronger than "T=1", or browse games against my own tiny nets: https://claude.ai/artifact/AFyWD39J5sN2RfRe7VbpUx
Comment · 3 months ago
Huh? The wiktionary link I included links to (Failspy's message in) this 2024 discussion about how and when and why it was coined (by failspy): https://huggingface.co/posts/mlabonne/866788930457283#67196f..., as well as another one.
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.
Comment · 3 months ago
Is there any evidence that would change your mind?
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
Comment · 3 months ago
I wnt and read your other comments.
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.
Comment · 3 months ago
Comment · 3 months ago
I understand basic multivariate calculus (almost every STEM degree teaches it, and I paid attention), which is enough to understand the problem if not every detail about the solution, so I can partially follow what Fable is doing and guess whether it gets too sidetracked.
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.
Comment · 3 months ago
The counterexample in the news cycle today helps better understand how the math works. I can't think of one that doesn't.
Comment · 3 months ago
I think many long-haul truckers work in pairs for this reason?
Comment · 3 months ago
By the CoT content, this is a screenshot of someone giving Fable the result and asking if it's true, not the CoT of discovery.
e.g. "maybe the user's example is DESIGNED to be "correct in the stated facts" &c"
Comment · 3 months ago
Yes. You could say this is the sound of silence.
Comment · 3 months ago
Apparently "onomatope" is a much less popular name for the same thing (e.g. Wikipedia uses my version).
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.
Comment · 3 months ago
It's an onomatopoeia
Comment · 3 months ago
But to be fair, ZK proofs have strong "Cryptography 2: the Dark Tower" (2cryp2graphy?) vibes.
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)
@AurSaraf sonoflilit at everyone's favorite email service
meet.hn/city/il-Tel-Aviv
Socials: - github.com/sonoflilit - linkedin.com/in/aursaraf
Interests: Climbing, Entrepreneurship, Fintech, Freelancing, Hacking, Open Source, Programming, Startups, Technology
---