So here are some thoughts about coding and LLMs that have nothing to do with agents, Cursor, or the economy! Instead, let’s talk about something minor but useful if you’ve got the need: Recognizing handwritten text! For the past 2 months I’ve been building an app to digitize my handwritten diaries from years ago and LLMs make a huge difference in handwriting recognition.
Example: This is a page from my diary from 1995. Next post will be the best VNRecognizeTextRequest could do with the image. True, it’s local and free! But also barely readable. Useful for full-text indexing of images but not much more.
24 Many
> Hostel
> 1:15 am
> Tow a' writing. I might take tomorrow off and
> try to catch op an writing, and other wite relax.
> I speat the early afternoon a the Than kill.
> I chopped into the Proguensive Unionist Party
> ffice and picked up 3 interviews sell a
> follow up for Friday. The I trucked back
> to the hostel and almost missed Pand, who
> took me to meet Mre. Evehyn Dickuson, Belfust
> midut 153 years. I havent recopied that
> intevienz yet.

Contrast with gpt-4o!

> 24 May
> 1:15 am
> Hostel
>
> Ton o' writing. I might take tomorrow off and try to catch up on writing, and otherwise relax. I spent the early afternoon on the Tunkill. I dropped into the Progressive Unionist Party office and picked up interviews and a follow-up for Friday. Then I trucked back to the hostel and almost missed Paul, who took me to meet Mrs. Evelyn Dickerson, Belfast resident of 53 years. I haven't recorded that interview yet.

I've used gpt-4o to transcribe 1,308 pages of diary entries spanning 9 years of my life (age 14 to 23). I've got 4 more volumes to go. I love having them backed up and searchable! I've been meaning to do this for ages and I'm glad it's finally possible.
My app in a screenshot: