HackerTrans
トップ新着トレンドコメント過去質問紹介求人

coulix

no profile record

コメント

coulix
·18 日前·議論
True, same conclusion, but the few samples I tried showed some real improvements since dec 2025 version.
coulix
·18 日前·議論
I wonder how it does compare to reducto, pulse, extendai.
coulix
·5 か月前·議論
Looking great, how did you standardized animations / canvas work? Did AI help?
coulix
·6 か月前·議論
The YouTube citation thing feels like a quality regression. For medical stuff especially, I’ve found tools that anchor on papers (not videos) to be way more usable like incitefulmed.com is one example I’ve tried recently.
coulix
·8 か月前·議論
We need to see Landing.ai DPT-2, from my tests its the best in term of ability to extract structure from complex tables so far.
coulix
·9 か月前·議論
This.

Any complex parent table span cell relationship still has low accuracy.

Try the reverse, take a complex picture table and ask Chatgpt5, claude Opus 3.1, Gemini Pro 2.5 to produce a HTML table.

They will fail.