what you need to do here is loosen up your own mind, it may be best not to make too much of a direct frontal attack on the problem — i.e. to sit down and try to think of ideas. The best plan may be just to keep a background process running, looking for things that seem to be missing. Work on hard problems, driven mainly by curiosity, but have a second self watching over your shoulder, taking note of gaps and anomalies.

[source]

Finding something I read a while ago #

In writing this blog, I often remember quotes or articles I read a while back which passed my salience filter. Finding them is surprisingly difficult. I use Reader for read-it-later and Reflect for personal knowledge management, but even with full-text and semantic search, there are sources in the long tail it takes me ages to manually dig up. In the end what worked for me was Perplexity:

Prompt:

I read a blog post from a software about the unreasonable effort Penn & Teller put into their tricks, with the anecdote of Penn burying cards around a park in winter so in spring he could lead someone to a spot and magically find their card buried underground. The blog was about how this kind of unreasonable effort is admirable and what results in extraordinary outcomes. Find me the blog post.

Response

There appears to be a misunderstanding in your recollection. The story you’re referring to is about Teller (not Penn) who buried multiple boxes in a park corresponding to different potential chosen cards, then waited months for grass to grow over them before performing the trick. The blog post you’re thinking of is likely Allen Pike’s “An Unreasonable Amount of Time” from December 31, 2024, which uses this anecdote to illustrate how magic sometimes comes from spending more time on something than anyone might reasonably expect. The key quote from Teller that inspired the blog post is: “Sometimes magic is just someone spending more time on something than anyone else might reasonably expect”.

That was indeed the blog I was looking for.

My tools couldn’t find it because they apply AI to post-process the search results, rather than pre-process them. A knowledge graph or RAG across the knowledge base would probably also have worked, which is essentially what Perplexity is doing but on a much larger scale.