Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI Engineer Claims to Have Cracked Linear A

aiclambake.com

Post reply on HN
Print view View original

91–100 of 195 posts

Re: AI Engineer Claims to Have Cracked Linear A

#91

Post by tamarru »

stratocumulus0 wrote: post #38

As an amateur who's been fascinated by this puzzle himself, I will add some context that might be relevant in assessing the plausibility of this claim: - The "Libation Formula", which the author used as the base for his translations, is the most studied piece of writing in Linear A, because it's the only recurring phrase (with grammatical variation) that we have. The corpus is extremely fragmentary, with just a handf…

Ciao. I'm Tom di Mino, and I'm on vacation in Bellingham, Washington right now. I'll get back to you later with a formal response.

I've also reached out to Dr. Ester Salgarella, so I'm familiar with attempts to apply computational analysis to the corpus, and where previous efforts erred.

Re: AI Engineer Claims to Have Cracked Linear A

#93

Post by yorwba »

_alternator_ wrote: post #80
stratocumulus0 wrote: post #38

As an amateur who's been fascinated by this puzzle himself, I will add some context that might be relevant in assessing the plausibility of this claim: - The "Libation Formula", which the author used as the base for his translations, is the most studied piece of writing in Linear A, because it's the only recurring phrase (with grammatical variation) that we have. The corpus is extremely fragmentary, with just a handf…

Thanks for the context; how do you think this impacts plausibility? Presumably the fact that he made progress in a well studied passage is cause for skepticism? What's your take?

Well, the reasoning in the article is that if you take A-TA-I-*301-WA-JA, keep only W-J and assume *301 starts with N, then you get a claimed Semitic root N-W-Y related to dwelling, except I wonder whether that shouldn't be N-W-H instead https://en.wiktionary.org/wiki/%D7%A0%D7%95%D7%95%D7%94 (Semitic isn't my area) so at best one fifth of one word matches two thirds of another therefore iT mUsT bE sEmItIc. A serious attempt at decipherment should at least try to explain the A-TA-I, or any of the other words in the sentence, for that matter.

Re: AI Engineer Claims to Have Cracked Linear A

#94

Post by ben_w »

TeMPOraL wrote: post #57
_verandaguy wrote: post #15

Earlier quoted context omitted.

This isn't really a reasonable approach, is it? The original prompts aren't provided, nor is the original context; even then, you can't really treat a stochastic system like an LLM as a major component in reproducibility.

> stochastic system Every day when you lower your butt onto your chair, you trust a stochastic system enough to assume you'll rest on the chair safely and not spontaneously phase through, which would lead to rather gory and painful terminal experience. Physics at macro scale is stochastic, which is a good reminder that stochastic != uniformly random. Expected distributions matter.

While strictly true, QM has such small standard deviations as to be irrelevant on the macro for things like bums and chairs.

IMO a better example would be the stochastic nature of quality control in manufacturing.

Re: AI Engineer Claims to Have Cracked Linear A

#95

Post by danishanish »

WhitneyLand wrote: post #54

If confirmed this is really cool and impressive work. Honestly curious how many years before it can be one shotted in a coding harness with Fable.next by someone who’s not a linguistics expert. Develop, test, and rank hypotheses about the phonetic values, morphology, grammar, and possible language family of Linear A using the full available corpus. Do not assume any decipherment is correct. Treat all candidate readin…

I don’t imagine a model capable of the first part would require being told not to assume a decipherment is correct

Re: AI Engineer Claims to Have Cracked Linear A

#96

Post by red_admiral »

stratocumulus0 wrote: post #52
Tuna-Fish wrote: post #35

The reason linear A is so difficult is that the total remaining corpus of Linear A text is ~7500 characters, spread out over ~1500 inscriptions. If you have a 4k screen, you can fit all remaining Linear A text on your screen at once, in 14pt high font.

An in addition to that, a vast majority of documents are lists which consist of a "header" (1 to 3 words) and word-number pairs afterwards. An another common class are small clay seals with 1, 2 characters carved into them. It's likely that in both cases, we may be dealing with abbreviations. Some of the lists end with "ku-ro" and a number that's the sum of all the previous numbers, oddly frequently off by one.

ku-ro obviously means "carry in" :)

Re: AI Engineer Claims to Have Cracked Linear A

#97

Post by red_admiral »

AaronAPU wrote: post #79
dehrmann wrote: post #43

Earlier quoted context omitted.

Very vaguely, it makes it like a one-time pad where it can be anything you want it to be. Not quite, but so little text leaves a lot of options open.

I wonder, is there a form of analysis which lets you quantify how ambiguous a set of symbols is? Maybe related to entropy? Obviously one symbol can mean literally anything, but you could also have very long strings of symbols with many different meanings.

Yes. Somewhere in Claude Shannon's work, called the "unicity distance".

Re: AI Engineer Claims to Have Cracked Linear A

#98

Post by simonw »

> Di Mino used Claude Code to build a suite of Python scripts that query, cross-reference, and organize the digitized Linear A corpus (drawn from the GORILA and SigLA databases), enabling systematic hypothesis testing at a scale that would have been impractical to do manually.

That's exactly the kind of thing I'd hope Claude would be used for in these kinds of projects - building tools, not black-box "solving" the problem.

Re: AI Engineer Claims to Have Cracked Linear A

#99

Post by Kosturdistan »

Sniffnoy wrote: post #83
Kosturdistan wrote: post #61

Earlier quoted context omitted.

The only write-up at the moment is my blog post, hopefully that changes in the coming weeks.

The blog post mentions a draft of a manuscript though. I was expecting something like a preprint. He's not willing to post that draft yet?

I have seen and read his draft article, he's not comfortable sharing it publicly yet since it's being reviewed by experts.

Re: AI Engineer Claims to Have Cracked Linear A

#100

Post by gus_massa »

kubb wrote: post #8
Kosturdistan wrote: post #2

A lot of loonies make this claim, but Tom's work is credible enough that it's being reviewed by linguistics experts at Rutgers and Cambridge. Additional validation: his approach produces results. He's translated over 300 words, and that's never been done before, and his solution actually solves some problems in Linear B. Tom is an AI engineer, and Claude Code was key to his work. Disclosures: I know Tom socially, and…

Let's wait until it's been verified.

I agree. The post has too few information. Also

>> reviewed by linguistics experts at Rutgers and Cambridge.

Here in Argentina, near 2005, we had like 5 guys that claimed to have 5 independent solutions of the Goldbach Conjeture. Each one got a PhD student that volunteer to read it, discussed the obvious problems with the author, tried to help to solve them and after a few months of back and forth they concluded that none of the solutions were correct or has an interesting insight. Nobody was surprised about the that, but some wanted to give them a try.

Until there is a official report by Rutgers or Cambridge, it doesn't mean too much.

>> He's translated over 300 words

Where is the table of translations?

Post reply on HN