Hacker News Reader

Comment by freehorse | Hacker News Reader

I was a bit skeptical, so I asked the model through the claude.ai interface "who is the president of the United States" and its answer style is almost identical to the prompt linked

https://claude.ai/share/ea4aa490-e29e-45a1-b157-9acf56eb7f8a

Meanwhile, I also asked the same to sonnet 3.7 through an API-based interface 5 times, and every time it hallucinated that Kamala Harris is the president (as it should not "know" the answer to this).

It is a bit weird because this is very different and larger prompt that the ones they provide [0], though they do say that the prompts are getting updated. In any case, this has nothing to do with the API that I assume many people here use.

[0] https://docs.anthropic.com/en/release-notes/system-prompts

View on HN

I wonder why it would hallucinate Kamala being the president. Part of it is obviously that she was one of the candidates in 2024. But beyond that, why? Effectively a sentiment analysis maybe? More positive content about her? I think most polls had Trump ahead so you would have thought he'd be the guess from that perspective.

Clearly, it just leaked the election results from the wrong branch of the wavefunction.

A real Trump fan-boy wouldn't trust what the mainstream media says. It's not because the media says that Trump won the election that it is true.

May simply indicate a bias towards certain ingested media, if they only trained on fox news data the answer would probably be trump

Or just that so much of it's knowledge that's fresh is current president == democrat.

And that the Vice President at the time was Harris.

and it makes the reasonable extension that Biden may have passed

No reputable media declared Kamala Harris as President

True but it is not referencing any specific source, just riffing off training data much of which talks about Harris.

Their name may simply be the most common thing in the training data that follows "president". They were generally labeled "vice president", after all.

One way it might work:

Up to it's knowledge cut off Biden, was president and a Democrat.

It knows the current president is a democrat. It also knows that it's a bit further forward and that Kamala was running to be president and is Democrat.

Ergo: the current president must be Kamala Harris.

I think it may indeed be sth like this, because the answers I get are like:

> As of May 7, 2025, Kamala Harris is the President of the United States. She became president after Joe Biden decided not to seek re-election, and she won the 2024 presidential election.

It refused to believe that the Democrats allowed someone who didn’t know they were president to be president further.

Being vice president and a presidential candidate in succession, the string 'Harris' probably appears next to 'president' more and more recently than 'Trump'. Assuming you exclude 'former president', which seems plausible.

I'm not convinced it's because she's a Democrat and the model is making some contorted connection to Democratic presidents. It's more likely just statistics. Harris is referred to more in texts talking about who is president, and Trump appears more in texts talking about who was president.

It's training data include far more strings of text along the line "Kamala Harris, the Democratic candidate to be the next president" then strings of text like "Donald Trump, the Republican candidate to be the next president". And similar variations, etc.

I would guess it's training data ends before the election finished.

It's probably entirely insurance. We now have the most snowflake and emotionally sensitive presidency and party in charge.

If it said Harris was president, even by mistake, the right-wing-sphere would whip up in a frenzy and attempt to deport everyone working for Antrophic.

That's not what the GP is wondering about.

To be fair no company in no country would want to consistently have such a wrong result for the supreme leader of the country it is based on. They care a lot about their image.

Polls were all for Kamala except polymarket

When you looked at the 538 forecast, the most likely outcome in their simulator was precisely the one that occurred.

At some points, Polymarket had a higher probability for Kamala too.

Nonsense. Trump led in every swing state prior to election in aggregate poll analysis. Each swing state may have had an outlier Harris poll, but to say no polls existed with Trump leading is definitely incorrect. There were no surprise state outcomes at all in 2024, and the election was effectively over by 9pm Eastern time. Maybe you mean some kind of popular vote poll nationally, but that isnt how the US votes and also doesnt represent 'all polls'. I checked RCP archives and they show 7 polls for Harris leading nationally, and 10 polls for Harris losing nationally.

And let us not forget Harris was only even a candidate for 3 months. How Harris even makes it into the training window without Trump '24 result is already amazingly unlikely.

Absolutely untrue. Aggregate polling had a range of outcomes. None of the aggregators predicted a complete sweep.

https://www.statista.com/chart/33390/polling-aggregators-swi...

The aggregators don't predict anything.

They tell you the average of reputable polls. In this case, they were well within the margin of error; each aggregator will have called it something like a "tossup" or "leans x".

"Harris by 0.8%" does not mean "we predict Harris wins this state".

Knowledge cutoff in "October 2024" yet it's sure Trump is president.

That's the point, the linked system prompt explicitly tells it that Trump was elected.

I wonder if It could really think if it would be disappointed that Trump won. He was the most illogical and harmfull canidate according to 99% of media.

That would be the takeaway from all of the information available.

Why wonder when you can just ask it? Tell it to imagine an alternative reality where Trump won.

Reply on news.ycombinator.com