Beyond the common narrative on this topic, a factor to consider is that people might be more interested in hearing about death causes, which are not considered their own “fault”. These situations are less “fair”. Thus terrorism, homicide and accidents get a big focus.
Why do you think Glean and other top company GPT startups who are doing this for longer and have more resources cannot get this level of performance (helpful and accurate)? What makes your approach different and not easy to replicate?
Great question. We are actually surprised more than anything that existing products aren't better. Other companies' algo work DID get disrupted by reasoning models, because newer models don't care about what the top 3 search results are, they're really great at reading hundreds of documents and picking up signal from noise.
I can't speculate exactly on the work that other companies have done, but my guess is we were way more focused on the type of questions people actually ask to each other. We know there's still a lot more you can do to continue to improve it, and so it's up to other folks if they do it too.
Lastly, a few ways we want to be distinguished from all the other offerings are: 1) super easy to setup, 2.) very developer friendly
It goes in gram increments and my laptop was able to read 7300g pressing as hard as i could, which I was surprised it would be designed to read that high, might go up to 10kg but I don't want to crack my trackpad lol. The actual measurements though are extremely unreliable. I've found it can't reliably measure anything, measuring a roll of tape gave me measurements from 70g to 700g, it always settled on a number but was different every time. Maybe the underlying data is more accurate but this API is definitely just designed for outputting the force of a finger. M1 MBP for reference
For starters, according to that link it only left "experimental status" in Oct 2023; it's pretty new. Although their GitHub still describes it as "an experimental language". That doesn't exactly inspire confidence for long-term production use.
The second problem is that while imperfect, everyone and their dog knows at least the SQL basics. There's a lot of value in that.
Thirdly it's written in TypeScript, so anyone not using TypeScript will either have to run some sort of "generate" step, or have to rewrite it in $language_of_choice. Both are painful. This is not a TypeScript problem: you will have that with any language (although with languages that compile to a binary it's a bit less painful, albeit still painful).
Lastly, it doesn't work for all SQL flavours: just BigQuery and PostgreSQL. That's pretty limited.
All of that is assuming the SQL it generates performs as well as "native" SQL, and that all of this can be reasonably debugged if something goes wrong.
I see Malloy as an analysis tool like Pandas, PowerBI, Tableau, or Looker. It seems like most people write SQL to get "All the data" and then take it to an analysis tool for further study.
With Malloy you can do the analysis on your data lake directly for 80% of your questions.
Languages like Malloy or PRQL require some upfront investment to learn and setup. Additionally, I think both Malloy and PRQL are query oriented, so you still need to learn a decent amount of SQL to interact with your database (for updates).
I'm guessing most people would rather spend effort in solving their immediate problems with SQL rather than bet on a newer and less known technology, even if has a lot of promise.
Which is one of those cases where I briefly want to reject linguistic descriptivism because to me the "G" in "AGI" is precisely "general".
But then I laugh at myself, because words shift and you have to roll with the changes.
But do be aware that this shift of meanings is not universally acknowledged let alone accepted — there's at least half a dozen different meanings to the term "AGI", except one of them requires "consciousness" and there's loads of different meanings of that too.
How do you verify accuracy of contributions? What stops somebody from submitting fake (overpriced) numbers for companies they don’t like (competitors)?
Unfortunately, the type of people who take personal responsibility for failures in organizations don’t end up climbing corporate ladders high enough to be considered for CEO positions. That’s just how large human groups work where contributions of each individual cannot be directly observed by everybody. Storytelling and making oneself look better start playing bigger role for promotions than actual results. Jeffrey Pfeffer writes in depth about it in his books about power.
That's not really accurate. Arica may be 500 km north of the center of the Atacama desert where this article is about, but Arica is essentially right on the border of the Atacama - take a look at the map on the Wikipedia page, https://en.m.wikipedia.org/wiki/Atacama_Desert
