Unverified: What Practitioners Post About OCR, Agents, and Tables
idp-software.com
idp-software.com
Even considering HNs no LLMs for comments rule, which I mostly agree with, I think we would all lose of the same rule were applied to publishing in general.
https://claytonwramsey.com/blog/prompt/
discussion: https://news.ycombinator.com/item?id=43888803
All of the output beyond the prompt contains, definitionally, essentially no useful information. Unless it's being used to translate from one human language to another, you're wasting your reader's time and energy in exchange for you own. If you have useful ideas, share them, and if you believe in the age of LLMs, be less afraid of them being unpolished and simply ask you readers to rely on their preferred tools to piece through it.
In the article you linked the output he is complaining about probably had a prompt like this: "What are the downsides of using Euler angles for rotation representation in robotics? Please provide a bulleted list and suggest alternatives." The LLM expanded on it based on its knowledge of the domain or based on a search tool (or both). Charitably, the student looked it over and thought through the information and decided it was good (or possibly tweaked around the edges) and then sent it over - though in practice they probably just assumed it was correct and didn't check it.
For writing an essay like "I would rather read the prompt" LLMs don't seem like they would speed up the process much, but for something that involves synthesizing or summarizing information LLMs definitely can generate you a useful essay (though at least at the moment the default system prompts generate something distinctively bland and awful).
How else do you think I would have come to write this comment? I got to the second major heading before realizing that there is little human input in this document.
I use LLMs but I will never impose on Claude's intellectual musings on another person as some sort of intellectual insight.
This is about the same as copying someone else's homework and then presenting the copied work as an example of deep brilliance. The copying isn't great, but the boasting is absurd. Who are we trying to con?
Never published an LLM text, friend.
And if somebody needs Claude to get something published, that person should find a better line of business, one more suited to her or his aptitudes.
> I would be genuinely interested in specific changes you would do if you were the editor.
This whole thing would get sent back with the kind request to think of an argument and write it out. By hand. Without an LLM.
In all fairness, I've been accused of sounding like an LLM this year, which is quite unfortunate as I think we're coming to the end of careful writing.
When I use an LLM, it tries to sound like me but there are still tendencies it falls back on, especially when the context window begins to expand.
The 'missing subject nouns' is probably the LLM's way of sounding like an authoritative source in a technical field since many programmers like to write that way.
https://lalitm.com/post/building-syntaqlite-ai/
Flags for LLM vs human drafting:
- Subtitles have the rhetoric turned to 11 with LLMs. (Note: Who has ever had multiple sentences as a blog post heading? It's bizarre) :
- LLM "The Demo Works. Production Does Not."
- Human "AI is why this project exist, and why it's as complete as it is"
- LLM "Six months ago, a practitioner could name a preferred OCR engine with confidence. Based on what I read, that confidence is gone." - *What was read?*
- Human "AI coding tools and playing slot machines"[ref]
- LLM *Scroll through—each thing is about the same length*
There are lots of tells like this. This is a moment to get good at detecting LLM text in case it's surreptitiously used to your detriment.
> Who has ever had multiple sentences?
Many? https://forum.wordreference.com/threads/two-sentences-in-a-t...
> Sources for claims that call for evidence
Absolutely. You got the joke, or? This was the main point of the full article. No primary sources. Only unverified aggregates. Strong contrast to what I did normally once per month.
> Variable paragraph lengths
I tried to compare it to the URL you posted. It's quite similar. I would have rather have said. Shorter sentences. Shorter Paragraphs. But let's not fight on this ;)
Think of an LLM that corrects 898,00 to 888,00. It feels like the David Kriesel Xerox case. Still, it's an interesting way to think of the issue of optical character recognition.
What I want is an output that records which sections of the image have contributed to each word/letter, preferably with per word confidence levels and user correctable identification information.
I should be able to build a UI to say: no, this section is red-on-green vertically aligned Cyrillic characters; try again.
Niels lately posted a lot about other OCR engines: https://www.linkedin.com/posts/niels-rogge-a3b7a3127_lots-of...
I did have it put confidence indexes next to the output per line, and that was pretty useless, they were either really high or really low, and the confidence didn't match the mistakes at all.
What worked: You use an OCR that provides character/word-level bounding boxes and let the LLM extract from data. Then the LLM is capable of "calculating" a confidence of extracted data.
biggest issue is OCR can't distinguish directionality - ie. if someone messages you, or you type "let's cancel the meeting" the text is identical but the intent isn't
Truer words have never been spoken. LLMs make mind blowing demos, but real-world performance is much less (but still useful).
An example from yesterday:
I asked Google / Nano Banana to repaint my house with a few options. It gave a nice write up on three themes and a nice rendering of 1/3 vertical slices in one image of each theme.
Then, I asked it to redraw the image entirely in one of the themes. It redrew the image 1/3 in the one theme I asked for and 2/3 in a theme I did not ask for. Further prompting did not fix it. At the end of the day, this was a useful exercise and I was able to get some sense of what color scheme would work better for my house, but the level of execution was miles away from the perfection portrayed in demos and hypester / huckster bloggers and VCs.