Top all-time · #21961
Maneesh Agrawala
Personal blog · magrawala.substack.comaidesign
Maneesh Agrawala writes Maneesh’s Substack, a personal blog at magrawala.substack.com about ai and design. Since 2023, 3 different Hacker News readers have linked it 3 times, most often “Unpredictable Black Boxes Are Terrible Interfaces”. The last post was in 2023, but the archive is still widely read.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
One comment links a Substack post that explores the limits of LLMs, offered as analysis in a thread on record-and-replay app automation and English prompts.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
My personal Substack.
Most-linked posts?
- Unpredictable Black Boxes Are Terrible Interfaces3 people · 3 mentions · first linked 2023-04-04
What Hacker News says?
Definitely, though the semantics of field mappings often only exist in a user's head, so will need to be explicitly defined. English prompts will no doubt be a big part of Plato, though. We're still figuring out exactly where the line is between English and traditional UIs. Have you read any good analysis on the subject? Here's one that explores the limits of LLMs: https://magrawala.substack.com/p/unpredictable-blac…
Comment linking /p/unpredictable-black-boxes-are-terrible
on “Macros: Automate Apps with Record and Replay”Submitted Unpredictable Black Boxes Are Terrible Interfaces as a story · 26 points
HN discussionSubmitted Unpredictable Black Boxes Are Terrible Interfaces as a story · 1 points
HN discussion