Monika Barget<p>Every now & then, I give <a href="https://akademienl.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a> a scan of my handwriting to test its skills in working with <a href="https://akademienl.social/tags/handwrittentexts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>handwrittentexts</span></a>. Initially, it responded that it could not process the scans or gave me entirely fictional output, but today it got almost everything right. These results are better than those I achieved with <a href="https://akademienl.social/tags/HWR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HWR</span></a> models in <a href="https://akademienl.social/tags/Tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tesseract</span></a> & <a href="https://akademienl.social/tags/OCR4all" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR4all</span></a> without additional training. I also asked ChatGPT what it "thought" about my writing & it called it "consistently shaped & large with stylistic strokes."</p>