Live data from Hacker News

Working with The Associated Press to provide fresh results for the Gemini app

blog.google

61–68 of 68 posts

Re: Working with The Associated Press to provide fresh results for the Gemini app

#61
post #23
post #9

Earlier quoted context omitted.

1.3% isn't great. I'd rather just go, and pay, directly to trusted news sources. Everyone has different tolerance for falsehoods and priorities I guess.

What's the error rate for human journalists? Based on my experience, I'd guess it's much higher than 1.3%.

As others have already pointed out, feeding these new articles aren't magically going to make them any more accurate. These hallucinations are going to be on top of any errors in the data sources.

I'm not replying to point that out, I think others have done a better job. It's mostly that this conversation made me think of this classic Babbage quote that I've always enjoyed.

"On two occasions I have been asked, – 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?' ... I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question"

Re: Working with The Associated Press to provide fresh results for the Gemini app

#62
post #13
post #9

Earlier quoted context omitted.

1.3% isn't great. I'd rather just go, and pay, directly to trusted news sources. Everyone has different tolerance for falsehoods and priorities I guess.

You’d have to pay quite a bit to get journalists to answer your questions specifically. The whole isn’t about generating news articles, it’s about getting the model up to date on facts so it can synthesize a newspaper for you. I’d say it’s a way to get journalists to be journalists again instead of clickbait composers - as long as the model doesn’t inject clickbait there itself. I don’t trust Google to not do it some…

> You’d have to pay quite a bit to get journalists to answer your questions specifically.

This isn't what I meant. I pay directly for subscriptions/donations to news organizations that employee journalists that do this original reporting. I don't want a middle man that just messes it up. This goes for LLMs and for free news sites that don't do much more than summarize original reporting. I've seen more than a few times where they inject opinions, mess up facts or put focus on what was originally a small side point in the article.

Re: Working with The Associated Press to provide fresh results for the Gemini app

#63
post #7

Earlier quoted context omitted.

Journalism is dying, killed by its own excesses and by the internet. Google is offering it life support. The other option is death.

"killed by its own excesses"?

Doubling and tripling and quadrupling down on behaviors that most consumers wish they'd stop doing. You used to work at Google so you must be familiar with how groupthink operates.

Re: Working with The Associated Press to provide fresh results for the Gemini app

#64

We've gone the whole way from decentralization and rebelliousness of the early internet and the landscape is becoming suffocatingly sterile (=lifeless). I'm much more excited about eventual emergence of underground homebrew models without any guardrails...

Yes. What do you think Grok AI's real-time information being sourced on posts of individual users (similar to early internet) as opposed to established media (like AP)?

Re: Working with The Associated Press to provide fresh results for the Gemini app

#65
post #64

We've gone the whole way from decentralization and rebelliousness of the early internet and the landscape is becoming suffocatingly sterile (=lifeless). I'm much more excited about eventual emergence of underground homebrew models without any guardrails...

Yes. What do you think Grok AI's real-time information being sourced on posts of individual users (similar to early internet) as opposed to established media (like AP)?

No, Twitter posts are not even close to the “old internet”. No one was paid to create ragebait.

We still argued, but we did it from a place of passion, not commission.

Re: Working with The Associated Press to provide fresh results for the Gemini app

#66

Earlier quoted context omitted.

My guess is that they’ll just stuff a few daily headlines into the prompt so that queries about current affairs have some context, rather than re-training the model. Total guess obviously.

RAG isn't re-training. You can have vector embeddings of all AP news in a vector DB, then when prompted, find related news via similarity search, and add the most similar (and thus related) ones to the context. Here's some simple example code in Go, for RAG with 5000 arXiv paper abstracts: https://github.com/philippgille/chromem-go/tree/v0.7.0/examp... (full disclosure it's using a simple vector DB I wrote)

Good point - possibly just a limited version of this, although I don’t know how they’d handle a rolling time window in the vector DB to limit results to just recent stories?

Re: Working with The Associated Press to provide fresh results for the Gemini app

#67
post #59

Earlier quoted context omitted.

And what are we going to feed into the models without the journalism?

Abrogate the direct primary inputs. Weather sensors. Wildfire cameras. Police scanners. Court proceedings. Changes to ordinances. New LLC filings. Bankrupcies. Birth records. Death records. The whole corpus of society that is automatically logged and used as the primary data for people to then perform research or develop journalism upon. That is what you siphon up. And in output you can mad lib out an article just li…

I recommend you find some journalists who's work you find impressive and ask yourself what types of passive inputs could have written pieces like that.

Re: Working with The Associated Press to provide fresh results for the Gemini app

#68
post #59

Earlier quoted context omitted.

Abrogate the direct primary inputs. Weather sensors. Wildfire cameras. Police scanners. Court proceedings. Changes to ordinances. New LLC filings. Bankrupcies. Birth records. Death records. The whole corpus of society that is automatically logged and used as the primary data for people to then perform research or develop journalism upon. That is what you siphon up. And in output you can mad lib out an article just li…

I recommend you find some journalists who's work you find impressive and ask yourself what types of passive inputs could have written pieces like that.

Those represent what 1% of the bulk output of the field if I had to guess? By volume most news is wire service a la terse AP reports that get reposted everywhere. And they have to be terse because it's breaking news and there is no time to opine beyond reporting the inputs mainly as they are in shortform.
Post reply on HN