Top all-time · #20512
Aman Rusia
Personal blog · arcfu.com/postaiprogrammingdesign
Aman Rusia's personal blog at arcfu.com covers ai, programming and design. Since 2023, 3 different Hacker News readers have linked it 5 times, most often “Why do LLM pelicans look like this?”. It is still writing: the last post was on 2026-10-14, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
Cited as a recent piece arguing that AI models are now tuned to the pelican-SVG benchmark task. A commenter uses it to support their call for more multi-dimensional model benchmarks.
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.
Personal blog and portfolio
Most-linked posts?
- Why do LLM pelicans look like this?2 people · 2 mentions · first linked 2026-10-14
- Occam's razor predicts which React from Figma design developers prefer2 people · 2 mentions · first linked 2023-08-23
What Hacker News says?
In light of recent pieces like "The Emperor Pelican Has No Clothes" ( https://arcfu.com/post/the-emperor-pelican-has-no-clothes/ ), I'd be more curious to see how 'PelicanBench' becomes more robust in the time to come -- I feel like all models are now benchmax'd on the standard pelican SVG rendering task and we need something more multi-dimensional. It would be great to have a script that prompts a model to render t…
Comment linking /post/the-emperor-pelican-has-no-clothes/
on “Muse Spark Open”Submitted Why do LLM pelicans look like this? as a story · 165 points
HN discussionSubmitted Occam's razor predicts which React from Figma design developers prefer as a story · 2 points
HN discussionSubmitted What's so hard about generating code from Figma? as a story · 2 points
HN discussionSubmitted Claude avoids JSON accuracy issue in tool calling as a story · 1 points
HN discussion