Live data from Hacker News

Show HN: The Probability Times

theprobabilitytimes.com

11–20 of 21 posts

Re: Show HN: The Probability Times

#11
post #6

Love the concept - though in the versions where Trump loses, you should probably say 'Trump says system is rigged, or election stolen, etc.' -- we all know he'll never concede when he loses.

I deliberately tried to keep the content neutral. The goal of the website is translating statistics to something tangible - not adding an extra sauce of assumptions to it!

Re: Show HN: The Probability Times

#12

Interesting concept, but some of the pictures are a bit weird. There’s one with Biden and Harris in a practically romantic embrace.

This was one of the hard parts of making this. I think I discarded about 70% of all generated images, and I was aware that the remaining 30% was still borderline sometimes.

I my blogpost, I have a few examples of the discarded ones, including one of Harris and Obama in a similar romantic vibe: https://nerology.substack.com/p/how-i-made-the-probability-t...

I think at some point in the prompt I literally said that they were not romantically involved.

Re: Show HN: The Probability Times

#13
post #5

> Donald Trump Concedes... Hm, maybe the prompt is too tightly constrained. There is historical precedent for Donald Trump refusing to concede a presidential race, as seen in the 2020 election when he did not formally concede to Joe Biden and instead launched numerous legal challenges, citing unsubstantiated claims of election fraud. But I concede that no such outcome is represented in the FiveThirtyEight dataset.

Indeed, I’m just piping FiveThirthyEight > facts > LLM. And what the LLM makes of that is what you’re seeing, I tried to brief it as dry as possible in the prompt!

Re: Show HN: The Probability Times

#14
post #6

Love the concept - though in the versions where Trump loses, you should probably say 'Trump says system is rigged, or election stolen, etc.' -- we all know he'll never concede when he loses.

I deliberately tried to keep the content neutral. The goal of the website is translating statistics to something tangible - not adding an extra sauce of assumptions to it!

You can be politically neutral or factually neutral - not both. Seems like you chose the former.

Re: Show HN: The Probability Times

#15

Earlier quoted context omitted.

I deliberately tried to keep the content neutral. The goal of the website is translating statistics to something tangible - not adding an extra sauce of assumptions to it!

You can be politically neutral or factually neutral - not both. Seems like you chose the former.

In what way is this factually not neutral?

Re: Show HN: The Probability Times

#18
post #17

Jokes aside, I feel like this is how journalist work. They need to have news ready for both outcomes

Yeah! I see this in soccer all the time --- interesting indeed. I wonder if they need to pick several cases (a tight win for team A, for team B, a draw, an embarrassing loss of A, for B, ...)

Re: Show HN: The Probability Times

#19

Earlier quoted context omitted.

I deliberately tried to keep the content neutral. The goal of the website is translating statistics to something tangible - not adding an extra sauce of assumptions to it!

You can be politically neutral or factually neutral - not both. Seems like you chose the former.

Are you claiming this because you believe one side has a monopoly on the truth?

Re: Show HN: The Probability Times

#20

Earlier quoted context omitted.

You can be politically neutral or factually neutral - not both. Seems like you chose the former.

Are you claiming this because you believe one side has a monopoly on the truth?

No, I'm claiming this because reality and facts have a liberal bias.
Post reply on HN