pcraig3

It handles hundreds of thousands of requests a day, that's pretty good!

But you are right, SOC2 is the next step for sure.

Like Phil, I always assume the negative comments have a 35% accuracy rating.

I hope your child builds the next unicorn startup using this API!

You can try and run it yourself but you are going to need Stargate-level hardware to do it.

Sorry to hear you are out.

I've found "T/F" vals are not always portable between languages ("True" in Python vs "true" in JS) whereas integer comparisons are always interpreted correctly.

The job of Prognosticating Groundhog has weathered many technical revolutions: I don't think AI is going to be the one that puts them out of business.

Groundhogs are public figures who receive lots of press coverage, so it's important that we have mechanisms to keep them accountable.

Articles like "Grading the groundhogs" are only possible with clean datasets: https://www.noaa.gov/heritage/stories/grading-groundhogs

Yes, important context

Hello all,

LLM hype is everywhere these days, but actual usage data is pretty hard to find. I see tons of companies pushing AI tools at me but I have almost no idea what user behaviour/preferences are.

I built a TaxGPT.ca, an AI chatbot for answering people's (Canadian) tax questions and ran a bunch of numbers over the questions submitted between March 4 to April 31, 2024.

Highlights include:

- Over 8,500 questions answered - Users frequently asked about basic tax info and business expenses - Feedback is not very common but surprisingly positive - Experiments in tagging questions in relevant and for 'complexity'

My verdict here is that these bots have potential but you have to have really quick feedback loops and pretty good product chops — you can't just throw AI at some problem and assume users will find their own ways to make it useful.

I know, and not only are they fewer, but they are also mostly not real, alive groundhogs once you get that far.

The pictures of real groundhogs are all there in the individual profiles, it just turns out that half of them are stuffed.

Groundhog Day is on Feb 2nd! Depends on your timezone when the site rolls over though.

Yes sir. Not sure how it ended up there.

Fixed! Thanks for pointing it out. Bath pathname.

Interesting point, I've got a page up that is the reverse of that here: https://groundhog-day.com/alternative-groundhogs

On the other hand, there is an API as well, so you can build a custom groundhog dashboard if you like.

Absolutely: https://groundhog-day.com/api

> How often do they correctly predict the weather?

I mentioned this in another comment, but accuracy data is basically impossible to get. You have to get weather data year by year for different regions of the country and then compare them to historical ranges. Means a pretty huge amount of trawling through data, not a lot of payoff.

> Also how often did their right or wrong predictions contradict the majority?

This one, you can get a little more easily. Check out the predictions page to see them grouped by year: https://groundhog-day.com/predictions

If you are looking up a specific groundhog, you can see how often they align/differ from the plurality.

That's a huge insight to take away. Nevertheless, we still have climate-denier groundhogs consistently predicting winter and being wrong about it (cough Phil cough).

Hopefully, this site helps shine a light on these unscientific groundhogs.

Nobody else seems to do this outside of the US and Canada.

You, sir, have identified a bug. Just pushed an update to fix this.

If you look at the past 3 years, they have all been "early spring": https://groundhog-day.com/predictions

So the logic that was there didn't actually work properly, but I never noticed it before.

Accuracy data is basically impossible to get. You have to get weather data year by year for different regions of the country and then compare them to historical ranges. It will basically mean 10x the work I've done already. It's open-source though, so it could be that someone wants to collaborate with me in future :D

Thanks! It was a fun project for sure: no ads and nobody trying to get me to make it look more conventional.

I didn't know there were so many, and I also didn't know that so many of them aren't real groundhogs.

I have a pet theory on this.

I think, as a local councillor/politician, you show up to a Groundhog Day event and there are like 50 people there hoping you say it's gonna be spring soon, and so you just tell them that it will be.

However, it doesn't seem to be holding for this year, where most have said longer winter so far: https://groundhog-day.com/predictions/2023

The clean and breathable, machine-readable, all-regional data source for Groundhog Day forecasts. Find your fave groundhog, peruse past predictions, or trek the continent-wide Groundhog Map.

Includes enterprise-grade API for corporate use cases.