[HN Gopher] Do LLMs identify fonts?
       ___________________________________________________________________
        
       Do LLMs identify fonts?
        
       Author : alexmolas
       Score  : 57 points
       Date   : 2025-07-31 14:56 UTC (4 days ago)
        
 (HTM) web link (maxhalford.github.io)
 (TXT) w3m dump (maxhalford.github.io)
        
       | Doohickey-d wrote:
       | I'd be curious how much better a more expensive LLM would do -
       | gpt-4o-mini and gemini-2.5-flash-preview-05-20 are definitely not
       | the most capable LLMs one could have chosen.
        
         | double051 wrote:
         | Maybe they're just cheap and fast enough for the author to
         | perform an affordable analysis?
         | 
         | I agree that using the frontier models would be much more
         | interesting.
        
       | Workaccount2 wrote:
       | Maybe I simply don't know how advertising works, but wouldn't it
       | be totally possible that these fonts are just one-off drawn in
       | text?
        
         | rubyn00bie wrote:
         | I would say there's a good chance they could be one-offs
         | created by whoever was doing the ad. If you're paying an
         | artist, having them do the lettering could certainly be cheaper
         | than licensing a font for the purpose (or developing a font
         | that'll never be used outside of one, or a series, of ads).
        
         | k3liutZu wrote:
         | My fellow designer friends would often do this. But they would
         | start from actual fonts and do slight (or more than slight)
         | adjustments to them to match what they wanted as an outcome.
        
           | bbarnett wrote:
           | Yes but if you mess with fonts too much, then this can
           | happen:
           | 
           | https://www.youtube.com/watch?v=snjCj0ntG8E
        
         | smallerize wrote:
         | The benchmark only evaluates responses once the community has
         | identified the font.
         | 
         | E.g. https://www.dafont.com/forum/read/569491/taylor-swift-
         | font-p...
        
           | empath75 wrote:
           | That isn't the font, you can look at it yourself, it doesn't
           | match.
        
             | tjader wrote:
             | To me it looks like the same font, but with letter spacing
             | reduced so the letters don't flow into each other nicely
             | but overlap a bit.
             | 
             | Edit: here's the same effect made on inkscape:
             | https://i.postimg.cc/TYV6K6bt/taylorswift.png
        
               | pessimizer wrote:
               | And no matter what, when preparing for print you're going
               | to mess with all of the kerning until everything looks
               | right or to get effects that you want. You don't just
               | accept the kerning of any font. The only reason to buy
               | expensive fonts is that you have to touch the kerning
               | less often.
        
       | micromacrofoot wrote:
       | How close are the wrong guesses? Fonts are fairly incestuous
       | because the shapes of the characters themselves can't be
       | copyrighted (only the code), so there are sometimes dozens of
       | clones of very similar fonts... especially on a free site like
       | dafont
        
       | gdudeman wrote:
       | Missing from the methodology: - was thinking on or off? (At least
       | for Gemini) - was web search allowed? - was tool use allowed?
       | 
       | It's quite likely LLMs don't "know" the fonts in the dataset, but
       | they could figure many of them out.
        
       | Rastonbury wrote:
       | I've asked LLMs to suggest fonts/similar fonts for me from
       | screenshots and seems like they are close enough to my untrained
       | eye
        
       | HocusLocus wrote:
       | Why don't you just ask the document creator?
       | 
       | Every time I turn around these days I encounter someone ready to
       | use an infinite amount of energy that is being paid for by other
       | people, to 'simulate' some analog process by temporarily taking
       | the reins of some data center that is burning megawatts of
       | energy. We are being given the reins for 0.5 seconds but very
       | soon the horse will gallop away unless we have a lot of money to
       | spend.
        
         | qezz wrote:
         | It's not always possible to ask the creator, especially for the
         | old pieces
        
           | mjburgess wrote:
           | In this case, it's seems it is highly likely to be possible:
           | https://www.studioheavenly.com/our-work/mira-wellness (1
           | google)
        
       | she46BiOmUerPVj wrote:
       | I would have never thought to not use "what the font"
       | 
       | https://www.myfonts.com/pages/whatthefont
        
         | pwython wrote:
         | Yea, I just used WTF to help that guy who was waiting 2 years
         | to find a font.
         | 
         | https://www.dafont.com/forum/read/522670/font-identification
        
           | squigs25 wrote:
           | WTF is often wrong, and actually, I don't think your answer
           | in the 2 year old thread is correct
        
             | StrangeDoctor wrote:
             | I agree I feel like it's just blatantly funneling me into
             | those dubious buy this font sites. I have somewhat better
             | success with http://www.identifont.com/ usually
             | 
             | I don't think the proposed font is correct either, I'm not
             | even sure the concept of font works for that example
             | though. Mainly the arches on the m are wrong, too arch like
             | and whereas the example is more teardrop.
        
         | Lemaxoxo wrote:
         | Op here. I tried what the font a bit but didn't mention it in
         | the article. I didn't get good results with it. Although it's
         | probably a good idea to ask it for a guess, and feed that to
         | the LLM too.
        
       | cormullion wrote:
       | I suspect that few professional (paid for) adverts use any fonts
       | from dafont.com, and many fonts would anyway be unavailable to
       | ordinary users. The current font recogniser programs are usually
       | trained on commercially available fonts
        
       | StellarScience wrote:
       | With the latest Microsoft Word, if you open a PDF that is a
       | _scanned image of a document_ and convert it to Word format, it
       | does a pretty decent job of not only OCR (optical character
       | recognition) but also picking matching fonts for various
       | sections.
       | 
       | I just tested this with my internet connection disabled and it
       | still worked. Since it's doing local processing, I suspect it
       | uses traditional OCR algorithms rather than LLMs.
       | 
       | As the article concludes, LLMs aren't magic, they're just one
       | useful tool to include in your toolbox.
        
         | aaroninsf wrote:
         | It's pretty easy to imagine an evolved mess of an open ad hoc
         | but broadly adopted ecosystem where LLM are surrounded by a
         | bewildering array of Node-like domain-specific extensions.
         | 
         | Security concerns aside (...) that sounds pretty useful.
        
           | StellarScience wrote:
           | Right, for example early LLMs were notoriously bad at math,
           | as they had been trained on language. They'd get simple math
           | right, likely due to "rote memorization", but couldn't do
           | basic arithmetic with 3-digit numbers. The common AI agents
           | seem much better now. I suspect they added separate math
           | processing logic and trained the LLMs to recognize when and
           | how to delegate to it, though I'm not certain of that.
           | 
           | Similarly coding-focused LLMs can access backend engines that
           | actually run the code and get feedback, either to show the
           | user or to internally iterate.
           | 
           | Having a whole host of such backend processors would be
           | great. Users still only ever have to interact using natural
           | language, but get the power of all these specialized tools in
           | the backend. There are some tasks LLMs can do, but special-
           | purpose algorithms may do better, faster, and/or with less
           | energy usage.
        
       | mopsi wrote:
       | I recently tried to identify a font from a screenshot of an ad
       | and used everything I could find, from WhatTheFont to LLMs. The
       | LLMs were hopeless at identifying the font from the screenshot,
       | but ChatGPT eventually led me to the correct result after I threw
       | away the image and started describing the font in plain text:
       | monospacing, a dot in the middle of the 0, and (presumably) wide
       | usage. It turned out to be Ubuntu Mono. It was surprising that so
       | many obscure fonts were suggested, none of which were even a
       | reasonably close match, while Ubuntu Mono was completely
       | overlooked.
        
       | elicash wrote:
       | Results here are bad, obviously, but it'll be interesting when
       | LLMs can not just identify fonts but unredact pieces of documents
       | in places where just a few words are removed by analyzing the
       | length of redaction, combos of letters that fit into it, and the
       | context.
        
         | lblume wrote:
         | Why would you even need LLMs for that? Notwithstanding context,
         | finding text that fits into a given bounding box is already
         | perfectly doable via a classical algorithm (in this case e.g.
         | based on dynamic programming).
        
           | elicash wrote:
           | > Notwithstanding context
           | 
           | This is actually quite important! Especially when you're not
           | talking about a single word/name but a group of several
           | words/names.
        
       | larodi wrote:
       | What makes us think font information made it into the traning set
       | atll, rather than something more along the line of "all chars
       | that look like this one are to be interpreted as 'a'". doesnt
       | need to provide font name for it.
        
       ___________________________________________________________________
       (page generated 2025-08-04 23:01 UTC)