Skip to content

Commit

Permalink
chore: ✨ add skrub
Browse files Browse the repository at this point in the history
  • Loading branch information
davidgasquez committed Jun 29, 2023
1 parent 86efa29 commit f21ef48
Show file tree
Hide file tree
Showing 7 changed files with 12 additions and 12 deletions.
2 changes: 2 additions & 0 deletions Antifragility.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,10 @@
Antifragility is a property of [[systems]] that increase in capability, resilience, or robustness as a result of stressors, shocks, volatility, noise, mistakes, faults, attacks, or failures. It's fundamentally different from the concepts of resiliency (ability to recover from failure) and robustness (ability to resist failure).

- Antifragility is beyond resilience or robustness. **The resilient resists shocks and stays the same. The antifragile gets better**.
- Antifragile systems benefit from a process of trial and error. [[Experimentation]] and [[Learning]] from failures are essential for improving and evolving.
- [[Evolution]] is antifragile.
- In a stable system, animals won't evolve. In a volatile system, they will.
- [A little bit of disorder is good](https://astralcodexten.substack.com/p/book-review-antifragile). [[Evolution]] is a system that allows volatility rather than unwisely trying to buffer against it.
- Being exposed to [[evolution]] sucks - animals very often die. Perhaps it would be much kinder if somebody gave unfit animals some food to prevent them from starving. But such kindness would prevent natural selection, and gradually weaken the species (or, more technically, the species' suitability to its niche) until eventual cataclysm.
- [On areas with frequent catastrophes, where the catastrophes have externalities on people who didn't choose them, you want to lower variance, so that nothing ever gets bad enough to produce the catastrophe. In an area where people can choose whatever they want, and are smart enough to choose good things rather than bad ones, you want to raise variance, so that the best thing will be very good indeed, and then everybody can choose that and bask in its goodness](https://astralcodexten.substack.com/p/more-antifragile-diversity-libertarianism).
- Maintain a portfolio of options and avoid being locked into a single path. Having multiple choices allows you to benefit from positive Black Swan events while minimizing the impact of negative ones.
2 changes: 1 addition & 1 deletion Coordination.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
- The requirements to govern a commons without tragedy:
- Clear boundaries.
- Managed by locals.
- In a small community, everybody knows everybody, and can keep track of what they do. This makes small groups iterated games which rewards trust and penalizes sociopathic behavior.
- In a small community, everybody knows everybody, and can keep track of what they do. This makes small groups iterated games which rewards trust and penalizes sociopathic behavior.
- Community makes its own rules.
- Community can monitor behavior.
- Graduated sanctions for those who violate community rules.
Expand Down
1 change: 1 addition & 0 deletions Datathons.md
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
### Scikit Learn Compatible Transformers

- [LEGO](https://github.com/koaning/scikit-lego)
- [Skrub](https://github.com/skrub-data/skrub)
- [Skoot](https://github.com/tgsmith61591/skoot)
- [Sktools](https://github.com/david26694/sktools)
- [Scikit-Learn Related Projects](https://scikit-learn.org/stable/related_projects.html).
Expand Down
1 change: 0 additions & 1 deletion Open Questions.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@ Inspired by [Gwern Questions](https://www.gwern.net/Questions), [Patrick Colliso
- [What's the best way of teaching kids how to think?](https://news.ycombinator.com/item?id=24638756)
- [How can schools be optimized?](https://astralcodexten.substack.com/p/book-review-the-cult-of-smart)
- How does effective [[Parenting]] looks like?
- Is intelligence mostly innate? What can we do to improve it?
- [Are nootropics useful?](https://www.gwern.net/Nootropics)
- How can [Genetic Engineering](https://www.youtube.com/watch?v=jAhjPd4uNFY) do good and [how can it go badly](https://www.youtube.com/watch?v=n__42UNIhvU).
- What happens when we start [[DNA Genetic Testing and Analysis|tinkering with our genes after improving our health]]?
Expand Down
6 changes: 2 additions & 4 deletions Parenting.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,10 +19,8 @@
- Clearly communicated consequences ahead of time works much better than punishment.
- Raising responsible humans requires giving them responsibility, the opportunity for soft failures to learn from and having those awkward long talks and figuring out how to set healthy boundaries.
- Allowing kids to have lots of small failures. Whenever you can, let them experience a small consequence that won't be too bad.

* Allow them to experience the natural consequences of their actions as much as possible, both good and bad. Even if it has a negative consequence for them, as long as it's not too much.

* Aim to be as predictable as possible. The brain is a prediction engine and hates surprises, so minimize the surprises they have to deal with.
- Allow them to experience the natural consequences of their actions as much as possible, both good and bad. Even if it has a negative consequence for them, as long as it's not too much.
- Aim to be as predictable as possible. The brain is a prediction engine and hates surprises, so minimize the surprises they have to deal with.

## Resources

Expand Down
8 changes: 4 additions & 4 deletions Social Media Issues.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
- Internet algorithms are [[Systems|complex profit-maximizing systems]] that want to spoon feed you whatever you're most likely to click on. This is a win-win, symbiotic relationship—until it's not. When the algorithm is luring in your primitive mind against you, the relationship is parasitic. [The algorithm will learn to show thing that will further confirm and strengthen your existing viewpoints](https://www.ted.com/talks/eli_pariser_beware_online_filter_bubbles).
- Each app is competing against the other apps. Only the apps that grains your [[Focus|attention]] continue. Over time, your attention is more and more hacked by these apps. All exist to sell your attention to advertisers. Each one has a team optimizing the attention hackin[]()g.
- Social Media apps might be dangerous due to the amount of data they track. Data is not the new gold, it is the new oil, and it damages the social environment. [If you feel you are being watched, you change your behavior](https://www.socialcooling.com/). [Loss of privacy leads to loss of freedom](https://robindoherty.com/2016/01/06/nothing-to-hide.html). This may limit our desire to speak or think freely thus bring about “chilling effects” on [society—or social cooling](https://reasonandmeaning.com/2017/10/31/what-is-social-cooling/).
1. Your data is collected and scored.
2. Your digital reputation may affect your opportunities.
3. People start changing their behavior to get better scores.
4. As your weaknesses are mapped, you become increasingly transparent.
1. Your data is collected and scored.
2. Your digital reputation may affect your opportunities.
3. People start changing their behavior to get better scores.
4. As your weaknesses are mapped, you become increasingly transparent.
- Most of our [[news]] feeds are insular networks made up of people who get their info from the same filter bubble we do.
- [Social media makes more sense when you view it as a place people go to perform rather than a place to communicate](https://collabfund.com/blog/thoughts/).
- Social media provides an unfortunate filter: it dumbs down complex information. [Ideas don't pass perfectly from one person to another. Like a game of Telephone, the message gets mutated with each re-telling so, over time, ideas "evolve" to be more catchy, copy-able, contagious.](https://ncase.me/crowds/) The fittest ideas doesn't need to be true.
Expand Down
4 changes: 2 additions & 2 deletions Trip Planning.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,10 @@

- Select a theme and make sure everyone is in the same page.
- Agree on a budget ballpark before planning. This will make decisions easier down the road.
- Ensure you have similar budget expectations. This determines so many things! It's not just about paying equal share.
- Ensure you have similar budget expectations. This determines so many things! It's not just about paying equal share.
- Have a flexible schedule. Don't try to control things too much, it will never go as planned and you'll end up ruining your own personal experience.
- If needed, assign people or smaller groups to make decisions about certain areas (food, activities, ...). [[Coordination]] is hard when people are not paid to coordinate (work).
- You can assign a benevolent dictator to make decisions and organize people.
- You can assign a benevolent dictator to make decisions and organize people.
- Ask everyone to make a list of things they would like to see/do.
- Bring card/board games for long travel days.
- Search for "Walking" videos (tours) around the destination on YouTube.
Expand Down

0 comments on commit f21ef48

Please sign in to comment.