- In Gemini at least, if you look at how they process PDFs, they do an OCR and then feed the text + image to the model, without charging you for the text tokens (I believe).
So my guess is that Claude’s backend is doing the same — so this hack is probably more of a loophole in token accounting that might get closed if Claude is doing what Gemini does
- I tried the same thing last year (with openai models), back then it worked to reduce prompt tokens, but you needed way more completion tokens, ultimately more expensive (and slower)
https://pagewatch.ai/blog/post/llm-text-as-image-tokens/
- Ahhh my eyes the vibe coded readme
- This seems like a pricing hack that burns resources, that when the loophole gets closed the price of OCR will have to rise?
by himata4113
0 subcomment
- Related: https://blog.can.ac/2026/06/10/snapcompact/
by g42gregory
0 subcomment
- I think Oh-My-Pi (OMP.sh) uses images for context compactificaton. OMP is built on top of Pi coding agent.
by dimitropoulos
0 subcomment
- there's also a DeepSeek whitepaper on this technique https://www.seangoedecke.com/text-tokens-as-image-tokens
by troglodytetrain
0 subcomment
- So, just be careful with this, it very likely is switching to other less capable model hence the cost reduction. So looks like Fable but isn’t. So you are doing extra work when you could just switch the model back to opus 4.8 instead.
by OSaMaBiNLoGiN
1 subcomments
- Saw a Tweet a while ago from someone (maybe Carmack, maybe Geohot, maybe Karpathy?) wondering if images were just the better option.
Since then I've been using images with very simply worded prompts whenever I'm informing an agent of what is happening. Sometimes no text in the prompt at all.
It has been very very effective.
That being said, this isn't really what Karpathy was talking about. But it got me thinking a bit, and that got me to a much nicer workflow.
- I'm sorry, but this is retarded. It works, and it's clever, but but it's clearly a workaround for a pricing failure. Much like the bounty on poisonous snakes leading to people taking up snake-breeding, this just exploits and promotes waste. I think ultimately blame falls on Anthropic for the poor pricing system the enables such arbitrage. But I'm also disgusted by the inevitable tide of people exploiting this until its fixed, and creating an entirely unnecessary extra tide of digital junk.
- Tangentially related: I don't think OCR is the right term and I am generally vocal about that. But seeing this unquestioned here, I am wondering if I am the one who is wrong here. Is it ok to call this OCR? To me ocr means text in the end, not visual tokens.
- seems really dumb and like it would need to violate basic information theory to work?
input tokens are cheaper than output tokens. seems like it would maybe reduce input tokens at the expense of many more output tokens if you're actually triggering OCR via thinking?
- Reminds me of caveman: https://news.ycombinator.com/item?id=47647455
by electrotype
1 subcomments
- What about: "Read this document online : [URL]" and you add your text/context to an online document?
Would that reduce the number of tokens used too?
by tru3_power
0 subcomment
- This probably works with PDF parsing as well I’m sure, even if it’s just from not having to parse pdf format alone.
by puppycodes
0 subcomment
- That is hilarious and an amazing find.
by chickensong
0 subcomment
- Binary compression unpacked by OCR? This is the stuff of nightmares. So cursed, and yet...
- it is funny because nobody ever bother points out that they overcharge you for text input token price.
sure it was pretty resource intensity a few years before, but with turbo quant, sparse attention and various techniques, plus the advancing of hardware (dedicated prefill machine, memory pool for kv caching) the cost should be drastically reduced, and yet they still keep the same cost formula.
I can't help but laugh whenever someone proudly share how many billion input tokens they spent in their code sections and how much they saved with the subscription, meanwhile it is pretty much just electricity cost for the providers.
- Interesting approach, though that readme really needs a rewrite by a human...
by dippogriff
1 subcomments
- I want to see more text-free foundation models
by nickpeterson
0 subcomment
- a pictures worth a thousand tokens
- Are we really re-discovering that compressed binary formats are more efficient data representations?
- Isn't this basically what DeepSeek came up with https://github.com/deepseek-ai/DeepSeek-OCR
- a picture paints a thousand words
by felipelalli
0 subcomment
- No words.
- I cant get past that LLM intense slop text in the Github repo
- [flagged]
- [dead]
- [flagged]
- [flagged]
- [flagged]
Hacker News