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

A new Google model is nearly perfect on automated handwriting recognition

generativehistory.substack.com

Post reply on HN
Print view View original

141–150 of 328 posts

Re: A new Google model is nearly perfect on automated handwriting recognition

#141

Post by BirAdam »

snickerbockers wrote: post #104
brulard wrote: post #88

Earlier quoted context omitted.

This is quite a narrow view of how the generation works. AI can extrapolate from the training set and explore new directions. It's not just cutting pieces and gluing together.

uhhh can it? I've certainly not seen any evidence of an AI generating something not based on its training set. It's certainly smart enough to shuffle code around and make superficial changes, and that's pretty impressive in its own way but not particularly useful unless your only goal is to just launder somebody else's code to get around a licensing problem (and even then it's questionable if that's a derived work or…

You didn’t have to read the whole library because your brain has been absorbing knowledge from multiple inputs your entire life. AI systems are trying to temporally compress a lifetime into the time of training. Then, given that these systems have effectively a single input method of streams of bits, they need immense amounts of it to be knowledgeable at all.

Re: A new Google model is nearly perfect on automated handwriting recognition

#143

Post by terminalshort »

jstummbillig wrote: post #40
snickerbockers wrote: post #4

Earlier quoted context omitted.

I'm skeptical that they're actually capable of making something novel. There are thousands of hobby operating systems and video game emulators on github for it to train off of so it's not particularly surprising that it can copy somebody else's homework.

I remain confused but still somewhat interested as to a definition of "novel", given how often this idea is wielded in the AI context. How is everyone so good at identifying "novel"? For example, I can't wrap my head around how a) a human could come up with a piece of writing that inarguably reads "novel" writing, while b) an AI could be guaranteed to not be able to do the same, under the same standard.

If a LLM had written Linux, people would be saying that it isn't novel because it's just based on previous OS's. There is no standard here, only bias.

Re: A new Google model is nearly perfect on automated handwriting recognition

#144

Post by terminalshort »

mikestorrent wrote: post #114
testaccount28 wrote: post #42

Earlier quoted context omitted.

why would you admit on the internet that you fail the reverse turing test?

Didn't some fake AI country song just get on the top 100? How novel is novel? A lot of human artists aren't producing anything _novel_.

It was a real AI country song, not a fake one, but yes.

Re: A new Google model is nearly perfect on automated handwriting recognition

#145

Post by terminalshort »

observationist wrote: post #26

This might just be a handcrafted prompt framework for handwriting recognition tied in with reasoning - do a rough pass, make assumptions and predictions, check assumptions and predictions, if they pass, use the degree of confidence in their passage to inform what the other characters might be, and gradually flesh out an interpretation of what was intended to be communicated. If they could get this to occur naturally…

I don't see how this performance could be anything like that. There is no way that Google included specialized system prompts with anything to do with converting shillings to pounds in their model.

Re: A new Google model is nearly perfect on automated handwriting recognition

#146

Post by elphinstone »

I read the whole article, but have never tried the model. Looking at the input document, I believe the model saw enough of a space between the 14 and 5 to simply treat it that way. I saw the space too. Impressive, but it's a leap to say it saw 145 then used higher order reasoning to correct 145 to 14 and 5.

Re: A new Google model is nearly perfect on automated handwriting recognition

#147

Post by hopelite »

roywiggins wrote: post #132

My task today for LLMs was "can you tell if this MRI brain scan is facing the normal way", and the answer was: no, absolutely not. Opus 4.1 succeeds more than chance, but still not nearly often enough to be useful. They all cheerfully hallucinate the wrong answer, confidently explaining the anatomy they are looking for, but wrong. Maybe Gemini 3 will pull it off. Now, Claude did vibe code a fairly accurate solution t…

What is the “normal” way? Is that defined in a technical specification? Did you provide the definition/description of what you mean by “normal”?

I would not have expected a language model to perform well on what sounds like a computer vision problem? Even if it was agentic, as you also imply how a five year old could learn how to do it, so too an AI system would need to be trained or at the very least be provided with a description of what is looking at.

Imagine you took an MRI brain scan back in time and showed it to a medical Doctor in even the 1950s or maybe 1900. Do you think they would know what the normal orientation is, let alone what they are looking at?

I am a bit confused and also interested in how people are interacting with AI in general, it really seems to have a tendency to highlight significant holes in all kinds of human epistemological, organizational, and logical structures.

I would suggest maybe you think of it as a kind of child, and with that, you would need to provide as much context and exact detail about the requested task or information as possible. This is what context engineering (are we still calling it that?) concerns itself with.

Re: A new Google model is nearly perfect on automated handwriting recognition

#149

Post by AaronNewcomer »

The thinking models (especially OpenAI's o3) still seem to do by far the best at this task as they look across the document to see how the writer wrote certain letters where the word is more clear when it runs into confusing words.

I built a whole product around this: https://DocumentTranscribe.com

But I imagine this will keep getting better and that excites me since this was largely built for my own research!

Re: A new Google model is nearly perfect on automated handwriting recognition

#150

Post by nicpottier »

orionsbelt wrote: post #47
IAmGraydon wrote: post #41

Earlier quoted context omitted.

This is utterly wrong. Predicting the next word requires a large sample of data made into a statistical model. It has nothing to do with "understanding", which implies it knows why rather than what.

Ilya Sustkever was on a podcast, saying to imagine a mystery novel where at the end it says “and the killer is: (name)”. Saying it’s just a statistical model generating the next most likely word, how can it do that in this case if it doesn’t have some understanding of all the clues, etc. A specific name is not statistically likely to appear

I once was chatting with an author of books (very much an amateur) and he said he enjoyed writing because he liked discovering where the story goes. IE, he starts and builds characters and creates scenarios for them and at some point the story kind of takes over, there is only one way a character can act based on what was previously written, but it wasn't preordained. That's why he liked it, it was a discovery to him.

I'm not saying this is the right way to write a book but it is a way some people write at least! And one LLMs seem capable of doing. (though isn't a book outline pretty much the same as a coding plan and well within their wheelhouse?)

Post reply on HN