▲ 279 points
back
144 comments
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 could have a browser extension that could de-snarkify content before showing it to you. You could ask the LLM to preserve all factual content from the post, but to de-claw any aggressive or snarky language. If you really wanted to have fun, you could ask it to turn anything written in an aggressive tone into something that sounds absurd or incompetent, so that the more aggressive the post, the more it would make the author look silly.
This could have a double benefit. For the reader, it insulates them from the personal attacks of random strangers on the Internet. Don't get me wrong, there is a time and a place for real, charged arguments about important issues that affect us all. But there is little to be gained from having those fights with strangers; on the contrary, I think it poisons the body politic when strangers are screaming at each other.
For the writer, it takes away any incentive to be snarky or rude. If other people filter their content this way, there's no point in trying to be mean to them, and no "race to the bottom" for who can be more nasty.
This is the Soylent of written communication. Full nutritional value with an unremarkable flavor.
Kinda looking forward to something like this, as it has the potential to remove empty junk calories from the internet, hopefully leading to SIGNIFICANTLY less use of today's popular platforms.
My wish list:
- Eliminate ALL clickbait titles and ads. I only want to see a dry factual title.
- For any given topic, I only care about the main article (with the option to only see a summary, unless its a high quality blog) and couple of substantive comments, rest is junk I don't want to see.
The current state of popular social media sites has meant that I don't use it at all (except HN, which is trending in the same direction due to saturation with AI), but every other week or so I end up wasting a few hours, which I'd like to avoid entirely.
Ideally this would lead to 98% of content filtered/summarised out, and over time only use the internet for looking things up with intention. I want this to remove majority of "entertainment" value from the internet (by default) so that time/energy can be refocused in real life and high quality sources (books) only.
For YouTube, this already exists and I‘m using it. The extension is caller DeArrow and aims to reduce sensationalism via crowdsourcing, though I wouldn’t be surprised if top contributors are bots using LLMs.
I think it's an interesting idea to explore.
But... It's the type of idea that is unpredictable as it comes into contact with reality. If it works, it probably works very differently from the initial idea of how it will work.
Chrome PM for built-in AI APIs here.
I love this "de-snarkifier" idea and it seems to have broad interest. I couldn't resist hacking (well, vibe coding[1]) a "Snarknada" prototype to explore the viability, including patterns for low-latency and accuracy.
You’ve hit on exactly why we think on-device is the right move for this class of use cases. If you tried to "de-snark" an entire infinite-scrolling feed via a cloud API, the token costs would be astronomical for a developer. Plus, people (rightly) don't want to send their private social feeds or DMs to a third-party server just to clean up the tone.
Moving this to the device should make high-frequency "Semantic Mutation" financially and technically viable for the first time. If you (or anyone else) starts building this more seriously than my PM vibe coded toy, and hits specific friction points, I’d love to hear about them: it helps us prioritize the roadmap.
[1]: If you're using a coding agent (Cursor, Claude Code, etc.), I recommend pointing it to https://www.npmjs.com/package/built-in-ai-skills-md-agent-md. Most models were trained on the now-obsolete window.ai namespace, and this skill file helps them use the current APIs correctly.
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.
I've thought about this for HN which, now that it's become so big, just has a lot of aggressive negativity and snark. You'd probably run into the same problem as Usenet Killfiles: the folks that use Killfiles would see random orphaned conversations or would just miss large parts of threads while the people that don't have Killfiles would see a mess of toxicity that would make them want to leave. Likewise if you prompt filter your experience, you'll be separating your experience from everyone else's.
Though I hate the idea of this, I can see it becoming popular in some use cases, such as schools with "safe places".
I would love an app like this. I am a frequent user of https://www.boringreport.org/ for news, which does something like what you’re describing but for news articles.
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 feel that will just enhance the problems of social media than reduce it.
It kind of falls apart when you start to think of edge cases rather than "hey this tool will keep morons off my feed!" mentality
It is important, however, not intellectualise repugnant, racist, or inflamatory language; it deserves to be called out for what it is aimed at doing
And then we will understand reality even more. Only let the tech giants tell us what other people are expressing. Great idea
On the other hand it would make all comments sound the same and further dilute internet content into average slop.
I was literally just thinking that I’d like something like this for HN, which has become an incredibly bitter, cynical, and depressing place in the last decade. On virtually any story, most of the top comments are negative. Every major company is a greedy monster trying to destroy your life, every CEO is a sociopath, everything is terrible, all the time. I wonder how most HN users even get out of bed every day.
I led the design effort on this API, before retiring. Here's my writeup on some of the considerations that went into it: https://domenic.me/builtin-ai-api-design/
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 download is orders of magnitude greater than downloading the browser itself, and something that needs to happen before you get your first token back. That's unfixable until operating systems start reliably shipping their own prebaked models that an API like this could plug into.
This looks like it uses Gemini Nano under the hood. But the latest Gemma4 E2B and E4B models appear to be much better, so you'd probably be better off deploying quantized versions through an extension for now.
- Gemini Nano-1: 46% MMLU, 1.8B
- Gemini Nano-2: 56% MMLU, 3.25B
- Gemma4 E2B: 60.0% MMLU, 2.3B
- Gemma4 E4B: 69.4% MMLU, 4.5B
Sources:
- https://huggingface.co/google/gemma-4-E2B-it
- https://android-developers.googleblog.com/2024/10/gemini-nan...
Seems like a good way for a rogue JS script to offload token generation to a bunch of unsuspecting visitors
It would actually be pretty interesting to see if its possible to decentralize the compute to generate something useful from a larger prompt broken down and sent to a bunch of browsers using a subagent pattern or something like RLM, each working on a smaller part of the prompt
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 the app. Making something standardized that is cross-platform would be fantastic. It also needs to be on mobile devices, so the players that can easily make it happen are mostly Apple and Google. (Meta will follow or vice-versa I guess)
Key-point: it shouldn't be exclusive to promoted models.
(1) https://developer.apple.com/documentation/foundationmodels So the app would be able to query and get the right model(s).
We use this for summarising our hack day write ups: https://remotehack.space/previous-hacks/
It's a tiny script that looks up the rss feed and uses the content to generate summaries; quite a nice fit with our static site. Sometime I'd like to extend it to ask different questions about the content.
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?
Gemini Nano, unlike Gemma, is not open-weight, right? I would be interested in dumping the model weights, unless someone has done that already
The model this uses is useless for anything beyond 2 round chat at the most.
If you want to do anything interesting you need transformers.js and a decent mode. Qwen 0.9B is where things start working usefully
The better part of this is having a local-first AI, particularly because it has tool-calling builtin & structured output.
I haven't pushed out a full version[1] which uses ducklake-wasm + this to make a completely local SQL answering machine, but for now all it does is retype prompts in the browser.
"sorry, to use our website, you must have at least 22 GB of free disk space."
Fwiw - I did a fairly large comparison of Gemini Nano (the in browser ai model) vs a comparable free hosted model of Gemma (from OpenRouter) and the hosted model absolutely trashed the local model on every aspect of speed, reliability, availability, etc. [1]
I'm not particularly happy about that outcome as I wish we had more locally run AI models for reasons of privacy and efficiency, so this is more just a warning that at present there are some severe tradeoffs.
1 - https://sendcheckit.com/blog/ai-powered-subject-line-alterna...
Still in origin trial? Looks like they're adding a temperature parameter:
I’m just wondering how much more RAM and VRAM chrome will use after these changes
Is “Ship a 22gb model on your product” the new “put a chat window on your product”?
I agree with others this fits better in the OS, or hey maybe Apple sells a time-machine sort of NAS with neural engine chips.
I get the filtering use case here and I'd say the other one is personalisation of generic marketing copy.
Will this API and others like it will be a strong enough incentive to move away from Chromium based browsers and back on to Chrome?
Not long before all of the web content will be going through these AI pipelines where user might not even see original webpage.
trying to wrap it in a unix style CLI
see: https://github.com/Arthur-Ficial/fenster
and: https://news.ycombinator.com/item?id=47923692
hard work so far
Can pass to it the current page contents for a AI-based AdBlock / cookie manager / etc.?
Interesting. Questionable from a web standards POV, but interesting.
Who‘s gonna make it call tools?
Any chance this will be supported by Firefox or other browsers soon?
Imagine a Vendor API that adds a way to link from the page straight into a device purchase workflow. As a trial of the API in Chrome you can order a new Google Pixel 9b directly from any page with the word Android in it!
Or a LocalNet API that integrates with trusted hardware devices on your local network. As a trial (Chrome beta programme — strictly limited but here’s 3x signup links to share with your friends) you can adjust your Google Next Mini underfloor heating directly from Chrome!
Or a DirectCast API that lets you stream <video> elements to a device of your choice even over a VPN. As a Chrome trial, you can use your Google Cloud account to stream directly from YouTube Premium to any linked Google Chromecast devices you own!
Slightly off-topic: Refreshing to see these two authors link to their Bluesky and Mastodon profiles. No Twitter/X in sight!
Every time I see "prompt" nowadays, I'm briefly hopeful that I'm going to read something about $PS1. Then, inevitably, AI disappoints me yet again.
Domain names are a nice candidate for a Georgian tax