i have an amazing idea, lets take the top 1000 business books, condense their ideas down to 1 page each and remove all the fluff and sell this as a 1000 page book
That's what "The Personal MBA" book did
Readit Newsbluechar commented on Business books are entertainment, not strategic tools theorthagonist.substack.c... · Posted by u/ZeroTalent
In both of your transcripts it fails at solving it, am I failing to see something? Here’s my thought process:
1. The only option for who to take first is the goat.
2. We come back and get the cabbage.
3. We drop off the cabbage and take the goat back
4. We leave the goat and take the wolf to the cabbage
5. We go get the goat and we have all of them
Neither of the transcripts do that. In the first one the goat immediately eats the cabbage. In the second one the wolf eats the goat after you leave them.
If you take the goat first, the wolf will eat the cabbage. Reread the description - It's a twist on the old problem, to make it harder for bots to solve.
For years I've been asking all the models this mixed up version of the classic riddle and they 99% of the time get it wrong and insist on taking the goat across first. Even the other reasoning models would reason about how it was wrong, figure out the answer, and then still conclude goat.
o3-mini is the first one to get it right for me. Transcript:
Me:
I have a wolf, a goat, and a cabbage and a boat. I want to get them all across the river. If I leave the goat and the wolf together, the goat will eat the wolf. If I leave the wolf and the cabbage together, the wolf will eat the cabbage. I can only take one at a time. How do I do it?
o3-mini
1. Take the wolf across to the right bank.
2. Return alone to the left bank.
3. Take the goat across to the right bank.
4. Bring the wolf back to the left bank.
5. Take the cabbage across to the right bank.
6. Return alone to the left bank.
7. Finally, take the wolf across to the right bank.
Me:
I have a wolf, a goat, and a cabbage and a boat. I want to get them all across the river. If I leave the goat and the cabbage together, the cabbage will eat the goat. If I leave the wolf and the cabbage together, the wolf will eat the cabbage. I can only take one at a time. How do I do it?
o3-mini
1. Take the cabbage to the right bank.
2. Go back empty to the left bank.
3. Take the wolf to the right bank.
4. Bring the cabbage back to the left bank.
5. Take the goat to the right bank.
6. Go back empty to the left bank.
7. Finally, take the cabbage to the right bank.I've seen a post similar to this on multiple HackerNews threads over the past few years. It's likely part of the training set now.
bluechar commented on Cubic millimetre of brain mapped at nanoscale resolution nature.com/articles/d4158... · Posted by u/geox
bluechar commented on Notes apps are where ideas go to die (2022) reproof.app/blog/notes-ap... · Posted by u/pps
I used the Zettelkasten idea for a bit more than a year, and it was truly a joy to use. Unimportant idea get naturally forgotten, while important/relevant ones get reinforced and revisited a lot. Building the links feels like having a deep discussion with a knowledgeable friend, and, once in a while, you get that surprising insight when a note from a book about a completely different topic you forgot you read pops up and sheds a new light on your current reading.
But the main weakness of that system is what makes it so powerful: it is, by nature, extremely time consuming. It is so powerful because, in order to add the smallest note, you need to sift through dozens of them, amend them, thinks about connections, create notes for those connections... In a sense, it is the exact opposite of what the article describe: the system _prevents you_ to just jote a quick note and forget about it. I does make it very powerful as a "second brain", but I ended up finding that the joy and insights I got out were not worth the time investment. I guess this is a reason app builders do not emphasize the process: "get more out of your reading by spending a few more hours per day organizing your thoughts" is not super sexy.
I now see that system as relevant only to people whose _main_ focus is to collect information and extract new insights from them: philosophers, anthropologists, some types of sociologists... But if you just want to remember a blog post about weird CSS tricks, this is probably overkill.
> In a sense, it is the exact opposite of what the article describe: the system _prevents you_ to just jote a quick note and forget about it
Create daily notes (tied to the day you wrote them) or transient notes (tied to a concept) as scratch areas to quickly dump your thoughts onto the page.
Then return later when you have the time and focus to explicitly process your notes - either discarding daily/transient notes that are no longer interesting, or growing them into evergreen notes with sufficient detail and linking. Make sure it's easy to list all your daily and transient notes in an "inbox".
bluechar commented on Meta fined $1.3B over data transfers to U.S. wsj.com/articles/meta-fin... · Posted by u/jaredwiener
Apple CEO Tim Cook once said in an interview with MSNBC in 2018, "The truth is, we could make a ton of money if we monetized our customer - if our customer was our product. We've elected not to do that."
This statement had triggered Mark Zuckerberg to the core that they became foes over the disagreement [1].
[1]Breaking Point: How Mark Zuckerberg and Tim Cook Became Foes:
https://www.nytimes.com/2021/04/26/technology/mark-zuckerber...
For bases to work I need to split my stuff up into tiny documents but I'd prefer to have one big document with separate sections. For example I keep one document `book-recommendations.md` with many small sections for books I'd like to read. I can't search through that with bases unless I split those out into many small files in with one recommendation each.
https://github.com/blacksmithgu/obsidian-dataview