Reading Factfulness was an epiphany for me: our brains are wired to pay attention to the superdramatic in a way that is now harmful to it - the same way that preferences for sugar and fat are now harmful.
Factfulness helped to show me that, despite our brain's bias, the world is actually consistently getting better.
Do you have any recommendations for literature you like? (My experience in eye science matches yours - the literature is WAY ahead of what people believe)
Having a good prompt-engineering skill is the highest-leverage thing IMO, so I burnt 2 Max 20x usage windows to help Fable help me refactor mine. With its partnership we:
- Went deep on "what types of guidance even are there? what does giving good guidance mean?"
- Sampled my existing Claude guidance (CLAUDE.md, skills, hooks, etc.) and broke their guidance into "atoms"
- Categorized them by clustering, the same way Big Five was generated
- Generated a new candidate
- Then used independent agents to compare it against my existing corpus assuming that the new one would be worse
Working with it felt like working with a supersmart entity capable of generating very plausible-sounding but not-necessarily-true statements. The outcome certainly felt like an alien artifact, like nothing I'd make myself.
Only time'll tell if it holds up, but it sure had some interesting ideas.
I see this with my dad as he approaches retirement. I try to remind him that if he doesn't pay with money, he's going to pay with his time... and right now he's saving money he doesn't need for time he doesn't have.
2. rotate your hands so your index fingers are on the base of your skull, middle fingers just above
3. now put your index fingers on your middle fingers and "snap" them down on the muscle at the base of your skull some 10-15 times
4. if your tinnitus goes away or reduces, it's caused by muscle tension instead of nerves
This blew my mind when I first tried it, but looked into it and it makes total sense: we all work on computers all day, necks get fatigued, and the impact forces the muscles to contract until they force-release, alleviating the tension-caused tinnitus.
It pulled back Plan 9, and I was shocked: this is exactly what we need today, as I'm convinced we need to think about minimizing agent permissions the exact same way companies do. Plan 9 was just too early.
I've been wondering this too: for us, UUIDs are super opaque. But for an agent, two UUIDs are distinct as day and night. Is the best filesystem just blob storage S3 style with good indexes, and a bit of context on where everything lives?
One thing directories solve: they're great grouping mechanisms. "All the Q3 stuff lives in this directory"
I bet we move towards a world where files are just UUIDs, then directory structures get created on demand, like tags.
The guy to watch here is https://github.com/Dicklesworthstone . He's rewritten SQLite in Rust with fixes, written his own Rust async engine with fixes that Tokio doesn't have, generated an insane number of tools for agentic orchestration (indexing of all sessions across all harnesses, on-demand skill storage, agent mail), and is currently building out agent orchestration terminal multiplexer stuff.
Source: been watching both these guys closely, as I've been building my own agent factory focused on security + learning: https://github.com/mieubrisse/agenc
I think Gastown is truly special, but I wanted something more focused on learning as I think that's the real bottleneck. So I built AgenC to make it trivial to roll learnings back into your Claude.
I once took a timed test with a section that had me translating a string of symbols to letters using a cipher, response being multiple choice. If you read the string left to right, there were multiple answer options that started with the same sequence of letters (so ostensibly you had to translate the entire string).
But if you read the string right to left, there was often only one answer option that matched (the right one). So I got away with translating only the last ~4 symbols, regardless of how long the string was. I blew through the section, and surely scored high.
I always wondered: did they realize this? Or did it artificially inflate my results?
And looking at the highest-entropy section felt natural to me, but only because of countless hours as a software engineer where the highest-entropy bit is at the end (filepaths, certain IDs, etc).
Is it really accurate to say I'm "more intelligent" because I've seen that pattern a ton before, whereas someone who hasn't isn't? I suspect not.
Not nearly as cool as all the other stuff here, but still my favorite piece of tech for myself:
IMO, Vim + Markdown is one of the best ways to take notes, brainstorm, or just explore ideas. However, I found the questions of "Where should I put the notes in my dir hierarchy?" and "How do I find the notes again?" and "How do I ensure I have my notes across all devices?" to be inhibiting.
I wrote a CLI "journal" tool that says "forget putting them into folders", dumps all the Markdowns into a single Google Drive folder, and instead focuses on providing really good search.
Now, in my day to day, I can do "journal new some-meeting-with-dan.md" and I get a fresh Markdown. I can also do "journal find" to search by name, date of creation, or tag, and then open notes in either Vim or as rendered HTML in Chrome (for copy-pasting). Behind the scenes all the information is just encoded in the filename (so it becomes "some-meeting-eith-dan~2023-04-23T22:10:23~tag1,tag2.md", with no extra DB needed).
I'm also now trying to rewrite the frontend as a Charm TUI, which is another whole fun growth path!
https://github.com/mieubrisse/