https://hackerpaper.kaipfister.de/p/2108.11193/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=39729059urn:hackerpapers:mention:2108.11193:39729059Sat, 16 Mar 2024 20:08:39 GMT<p>Correct. Most image models to date have used very small text models, which are unable to spell many words (https://arxiv.org/abs/2108.11193) - if you cannot spell a word letter by letter because you don&#x27;t know what the letters are, how are you going to generate a pixel image of each of those letters...? (It is not as if letters were intrinsically hard. GANs were generating letters easily like 7 years ago.) Their general inability is due to BPEs and non-character-based tokenization. This was noted in the DALL-E 2 paper (https://arxiv.org/pdf/2204.06125.pdf#page=16&amp;org=openai), and it can be…</p><p><a href="https://hackerpaper.kaipfister.de/p/2108.11193/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL