Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Prompt API

developer.chrome.com

Post reply on HN
Print view View original

101–110 of 157 posts

Re: The Prompt API

#101

Post by duskdozer »

haberman wrote: post #16

This API seems perfect for an idea I've had for a while: a de-snarkifier for social media. Social media can be intellectually stimulating and educational, but it's also easy to get sucked into ideological sniping and flamewars, even if you didn't go looking for it. The emotional and intellectual energy spent flaming strangers on the Internet is a complete waste of human capital. With an API like this, I assume you co…

Or just ignore it. Or say you will not engage under [conditions]. Ultimately it will be you who looks foolish when the AI rewrote something incorrectly and you engaged with something that wasn't being said.

Re: The Prompt API

#102

Post by smalec »

haberman wrote: post #16

This API seems perfect for an idea I've had for a while: a de-snarkifier for social media. Social media can be intellectually stimulating and educational, but it's also easy to get sucked into ideological sniping and flamewars, even if you didn't go looking for it. The emotional and intellectual energy spent flaming strangers on the Internet is a complete waste of human capital. With an API like this, I assume you co…

[dead]

Re: The Prompt API

#103

Post by jimmypk »

tom1337 wrote: post #90

The idea of having local LLMs accessible in the browser for privacy concerning is nice i guess but when each browser has a different model attached to this API testing becomes even more a nightmare then now. I wonder if this will drive more users towards chrome because most of the usages of this API might be just tailored to fit the Gemini Nano model?

[flagged]

Re: The Prompt API

#104

Post by yearesadpeople »

haberman wrote: post #16

This API seems perfect for an idea I've had for a while: a de-snarkifier for social media. Social media can be intellectually stimulating and educational, but it's also easy to get sucked into ideological sniping and flamewars, even if you didn't go looking for it. The emotional and intellectual energy spent flaming strangers on the Internet is a complete waste of human capital. With an API like this, I assume you co…

It is important, however, not intellectualise repugnant, racist, or inflamatory language; it deserves to be called out for what it is aimed at doing

Re: The Prompt API

#105

Post by whattheheckheck »

haberman wrote: post #16

This API seems perfect for an idea I've had for a while: a de-snarkifier for social media. Social media can be intellectually stimulating and educational, but it's also easy to get sucked into ideological sniping and flamewars, even if you didn't go looking for it. The emotional and intellectual energy spent flaming strangers on the Internet is a complete waste of human capital. With an API like this, I assume you co…

And then we will understand reality even more. Only let the tech giants tell us what other people are expressing. Great idea

Re: The Prompt API

#106

Post by gruez »

2ndorderthought wrote: post #97
avaer wrote: post #4

It works, I've shipped this as a "local inference"/poor person's ollama for low-end llm tasks like search. The main win is that it's free and privacy preserving, and (mostly) transparent to users in that they don't have to do anything, which is great for giving non-technical users local inference without making them do scary native things. But keep in mind the actual experience for users is not great; the model downl…

Is it actually privacy preserving? Chrome mostly exists to extract all the information from a user it can without immediately getting a lawsuit of greater penalty than what is gained through ads, military contracts, etc. Android isn't too far off either. I would welcome any alternative to this. I can see applications for this being things like "while device is at rest and charging summarize all of the users recent te…

>I can see applications for this being things like "while device is at rest and charging summarize all of the users recent text communications" or whatever else as a legal loop hole for wiretap laws

This just exposes an API for sites to use. If they wanted to do the types of spying you're cynically suggesting, they could just add it without an API and you'd be none the wiser. Chrome contains closed source components so you wouldn't even know.

Re: The Prompt API

#107

Post by eis »

meander_water wrote: post #81
domenicd wrote: post #77

Earlier quoted context omitted.

I no longer have any inside knowledge, but from my time on this team they were very quick about getting the latest small (Google) models into Chrome. I expect that if Gemma 4 (or its equivalent Gemini Nano) isn't already in Chrome, then it will be soon. Note that the article here was last updated 2025-09-21, and as of that time it was already on Gemini Nano 3.

Thanks for the insider info! Do you know if there are any published benchmarks for Nano 3?

Google will soon release Gemini Nano 4 based on Gemma 4. A "Fast" version based on Gemma 4 E2B and a "Full" version based on E4B.

https://android-developers.googleblog.com/2026/04/AI-Core-De...

Re: The Prompt API

#108

Post by 2ndorderthought »

gruez wrote: post #106
2ndorderthought wrote: post #97

Earlier quoted context omitted.

Is it actually privacy preserving? Chrome mostly exists to extract all the information from a user it can without immediately getting a lawsuit of greater penalty than what is gained through ads, military contracts, etc. Android isn't too far off either. I would welcome any alternative to this. I can see applications for this being things like "while device is at rest and charging summarize all of the users recent te…

>I can see applications for this being things like "while device is at rest and charging summarize all of the users recent text communications" or whatever else as a legal loop hole for wiretap laws This just exposes an API for sites to use. If they wanted to do the types of spying you're cynically suggesting, they could just add it without an API and you'd be none the wiser. Chrome contains closed source components…

It's a lot easier to hide the language they need in a EULA for a feature like this than it would be elsewhere.

I appreciate you feel this is a cynical take. But have you seen the class action lawsuits against Google over the last 5 years? They exceed a billion dollars as far as I can remember and they are for more blatant things than this.

Re: The Prompt API

#109

Post by haberman »

altmanaltman wrote: post #52
haberman wrote: post #16

This API seems perfect for an idea I've had for a while: a de-snarkifier for social media. Social media can be intellectually stimulating and educational, but it's also easy to get sucked into ideological sniping and flamewars, even if you didn't go looking for it. The emotional and intellectual energy spent flaming strangers on the Internet is a complete waste of human capital. With an API like this, I assume you co…

Don't you think its better to just curate your social media and follow communities where the default is not toxicity? This is basically a distortion layer for reality and will just encourage more echo chambers. Also what is toxic to one person is not toxic to another depending on their subjective choices. How will you solve for this without everyone just seeing what they want to see even if reality is not like that?…

I'm inclined to think that this will actually decrease the power of echo chambers. Echo chambers become that way by policing dissent, either through moderation or through aggressive attacks on dissenters. A de-snarkifier would de-fang the latter.

I agree that what is toxic to one person is not toxic to another, but think that this is largely because many people enjoy seeing their perceived enemies attacked. In other words, it comes down to a viewpoint bias: attacking my group/viewpoint is toxic, while attacking other groups/viewpoints is good and noble.

My ideal is that a de-snarkifier would be strongly instructed to be viewpoint neutral; to filter based on whether the comment is being respectful, without regard to the views being expressed.

My idea would backfire if other people program their filter to reinforce their own biases by favoring content that they agree with and creating or amplifying personal attacks on their perceived enemies. That would be unfortunate, but ultimately we can only control what we do; each person gets to make their own decision.

Re: The Prompt API

#110

Post by elpakal »

rock_artist wrote: post #35

I think it's a step into a future of proper Model API. But it's just a small step. It reminds me of Apple's Foundation Models [1] While many AI integrations are focused on text communication / chat style. A lot of software benefits from non-text interfaces. I believe at some point OSes and browsers should provide an API to manage models so you'll have access to on-device/remote ones with a simplified interface for th…

Apple's Foundation models seem great on paper until you see the 4k context window. (though I know we are still early in this chapter).
Post reply on HN