In addition to everything everyone else has said: their math is off by half (or 100%, depending on how you count), due to a structural error.
(context: native English speaker, big reader, huge nerd, perfect SAT score)
I got all 100 correct on the first try without looking anything up! Confusingly, that only resulted in a "SCIENTIFIC ESTIMATE" that I know 85,000/~170,000 words?
Their "How is this calculated" page that appears at the end explains their error:
> According to the Oxford English Dictionary (Second Edition), there are approximately 171,476 words in current use.
> We use Stratified Sampling. Instead of testing random words, we divide the language into 5 distinct difficulty bands based on frequency of use:
> 1. Core Basics ~3,000 words
> 2. Intermediate ~7,000 words
> 3. Advanced ~10,000 words
> 4. Expert ~25,000 words
> 5. The Obscure ~40,000+ words
> If you answer 2 out of 3 'Intermediate' questions correctly, we estimate you know roughly 66% of the 7,000 words in that band.
> Total Score = Σ (Accuracy in Band × Band Size)
Their strata add up to 85000, not ~170k, making a perfect score still give a 50%.
They're also using a pretty limited and perhaps non-difficulty-representative subset of the language.
Also, I'd like to see the inverse of it: a model trained only on the last few weeks - or even minutes - of published information, or only on scientific papers published in the last year or two. Should present some interesting psychoses!
TALKIE-1930: Computers in the future may be employed in offices where calculations are required to be made, and where the nature of the business does not demand a very high degree of knowledge. The occupation will be a steady one, and the remuneration will be sufficient to afford a comfortable livelihood. The hours of attendance will probably be from ten to six.
USER: and digital computers?
TALKIE-1930: Computers who make use of machines will be distinguished from digital computers, who perform their operations by means of the fingers alone. The former will be employed in offices and public establishments, where a great number of calculations have to be made; the latter in private houses, and by individuals.
(for those confused, "computer" was, at the time, a human occupation)
Could they have crashed it because of security/safety concerns for President-elect Trump, who was there as a surprise guest, watching the launch with Elon?
Per NYTimes: “It was pretty epic on Attempt 1,” Kate Tice, a senior quality engineering manager at SpaceX, said of the last test flight’s tower catch on the company’s livestream. “But the safety of the teams and the public and the pad itself are paramount.”
Not sure what would have changed compared to the first launch, other than Trump’s presence - and they haven’t described any anomalies.
A launch is one thing: lots of explosive potential, but the kinetic energy is quickly dispersed.
The KE of a botched landing of what’s essentially a ballistic missile would be a whole lot more concentrated…
Or maybe they just didn’t have time to file a modified flight plan for it to enter even-more-specially-restricted controlled airspace.
* The FARS data is “normalized” by unpublished internal iSeeCars estimates of miles driven; the underlying “study” is a marketing blog post for their company.
* FARS data distinguishes between driver and occupant fatalities - the “study” looks only at occupant fatalities, which is not what most people would reasonably expect given the headline.
* One might reasonably suspect Tesla’s long history of touting 5-star safety ratings and advanced safety tech could lead to passengers being lulled into a false sense of security, and being less likely to use seatbelts.
Driver fatalities and seatbelt use are right there in the FARS data - one wonders why these weren’t considered and incorporated in the “study”.
Anyhow, a note to the HN user: don’t upvote FUD-sowing headlines based on blog posts about unscientific “studies” that are really just submarine PR; they carry none of the credibility of the underlying studies, and are a disservice to the scientists and public servants who rigorously and faithfully collect and analyze this data.
(context: native English speaker, big reader, huge nerd, perfect SAT score)
I got all 100 correct on the first try without looking anything up! Confusingly, that only resulted in a "SCIENTIFIC ESTIMATE" that I know 85,000/~170,000 words?
Their "How is this calculated" page that appears at the end explains their error:
> According to the Oxford English Dictionary (Second Edition), there are approximately 171,476 words in current use.
> We use Stratified Sampling. Instead of testing random words, we divide the language into 5 distinct difficulty bands based on frequency of use:
> 1. Core Basics ~3,000 words > 2. Intermediate ~7,000 words > 3. Advanced ~10,000 words > 4. Expert ~25,000 words > 5. The Obscure ~40,000+ words
> If you answer 2 out of 3 'Intermediate' questions correctly, we estimate you know roughly 66% of the 7,000 words in that band.
> Total Score = Σ (Accuracy in Band × Band Size)
Their strata add up to 85000, not ~170k, making a perfect score still give a 50%.
They're also using a pretty limited and perhaps non-difficulty-representative subset of the language.
Cute, but wrong on many counts.