For all TA lovers..
A basic and compressed learning on Fibonacci Ratios

💬 I often get Q’s like these:

How did you get your first customers for WIP? How did you grow BetaList’s traffic? Etc.

Makers are looking to reverse-engineer success. I see it everywhere.

I don’t think it works that way and the answers to those questions are mostly useless. 💥

I have built dozens of different products over the last couple of years. The vast majority failed. 😭

Surely if I know the answers to these questions, but still fail over and over again, these answers aren’t that useful. 🤷‍♀️

So what’s a better question to ask? 🤔

99.9% of the questions I receive are about the products that did well. In a way that makes sense, because we quickly forget about those that didn’t succeed.

🧠 This is known as survivorship bias.

Focusing on what survived, while ignoring what made it survive in the first place.

The real question, what you really want to know, is this:

What makes @WIP, @BetaList, and to some extent @AllStartupJobs succeed where my countless other attempts failed?

What separates a failed product 👎 from a successful product 👍?

Honestly, I don’t know. I wish I did.

It’s like Steve Jobs said “I’ll know it when I see it.” 👀

Same is true when we make products. We don’t know upfront what will work. But once we see an inkling of a product that does have potential, it’s not that hard to spot.

After 17 years and more than 300 races, it could be @alo_oficial's last F1 race on Sunday 😭 He's given us a lot over the years... including some superb GIFs!

Here we have a rare example of a GIF you can actually hear. TOMA. 💪

The Spanish Samurai

Never give up. 💪 #GraciasFernando

Winning is everything. #GraciasFernando

A thread on how absurd the UK is on transgender issues and how the UK got so transphobic

In 2015 Parliament held an inquiry looking into the state of Transgender equality. Trans people of all stripes outlined many different problems across many, many different areas.

As a result Parliament created a list of recommendations including legal recognition for non binary people, gender recognition act reform, allowing 16 year olds to change their legal gender and reform of NHS gender identity services.

The government under Theresa May ignored everything that was recommended except for Gender recognition act reform. This act came into law in 2003 and gave trans men and women (but not non-binary people) the ability to legally change their gender on their birth certificates.

The process at that time to change your birth certificate under the GRA was to make an application to a panel of cisgender people who would decide if you were sufficiently trans based on your payslips, photo ID and bank statements. You would not get the option to speak to them.

(Also this process cost £140 which is just a tax on being trans)

1/ Recently, I learned about the concept of ‘struggle porn’. This refers to the fetish of sacrificing nearly everything (health, relationships, time) for your startup. I fear that this label is creating more harm than good.

2/ @nateliason wrote a fabulous article about this topic, which first introduced me to this concept. Everyone should read it:

3/ @alexisohanian also recently spoke about struggle porn, though referring to it as ‘hustle porn.’ (as the co-founder of @hustlefundvc, obviously I take issue with this pejorative definition of ‘hustle’, but that’s another topic)

4/ Struggling in itself isn’t necessarily bad. Let’s be real here--if you’re going to start a startup, you will struggle. Founders should expect to work harder generally than employees. You will be challenged in many ways and also be super rewarded in others. This is normal.

5/ However, if you are over-indexing on hard work without clear purpose and degrading your mental health/relationships in the process--then this is very bad and we obviously should not celebrate this behavior.

Important paper from Google on large batch optimization. They do impressively careful experiments measuring # iterations needed to achieve target validation error at various batch sizes. The main "surprise" is the lack of surprises. [thread]

https://t.co/7QIx5CFdfJ

The paper is a good example of lots of elements of good experimental design. They validate their metric by showing lots of variants give consistent results. They tune hyperparamters separately for each condition, check that optimum isn't at the endpoints, and measure sensitivity.

They have separate experiments where the hold fixed # iterations and # epochs, which (as they explain) measure very different things. They avoid confounds, such as batch norm's artificial dependence between batch size and regularization strength.

When the experiments are done carefully enough, the results are remarkably consistent between different datasets and architectures. Qualitatively, MNIST behaves just like ImageNet.

Importantly, they don't find any evidence for a "sharp/flat optima" effect whereby better optimization leads to worse final results. They have a good discussion of experimental artifacts/confounds in past papers where such effects were reported.