insin

I thought they meant turning that page into a YouTube-like view (being able to filter by channel would also be very cool, though), I was going to do something similar in my own HN extension, but after trying an initial lazy embedding approach [1], asking for declarativeNetRequestWithHostAccess to be able to bypass HN's Content-Security-Policy feels icky.

Having https://i.ytimg.com in img-src (for thumbnails) and https://www.youtube-nocookie.com in frame-src (for embeds) would be nice :)

Edit: you can use YouTube's oembed endpoint to get channel details for a video, e.g.:

https://www.youtube.com/oembed?url=https%3A%2F%2Fwww.youtube...

[1] https://imgur.com/a/hacker-newstube-g1BQ7lf

What are the odds the next version of macOS reverts most of what happened in Tahoe? After having it forced on my work MacBook, I will not willingly install that trash UI on any device I own.

Sir, have you heard of our lord and saviour, Markdown?

The large business I work for cited low usage when they blocked it from being installed a couple of years back.

There's no real evidence for it but it is scientific fact that every Hacker News thread that's more than 7 deep is just a war between terrible metaphors.

This had me checking if anyone has implemented first-class support for Python JSX components in Django yet, and it could be... sort of... maybe viable with PyJSX? [1]

It looks like you'd have to implement something equivalent to provider/context functionality yourself if you want it, as well as a simple render()-like helper to render a component tree. I've not tried their VS Code plugin, but it's a good sign that they have one.

[1] https://github.com/tomasr8/pyjsx

A strange omission given that it's also The Perfect Agentic Coding Language.

You first, define "conscious" ;)

They've made / completely focused on the repos that you own and work on (and added some Copilot stuff I can't see because I don't use it), instead of the social media-like "Feed", which is now on a separate /feed page.

Opting out just makes the Feed appear on / again. I'd rather they just give you the option instead of doing the opt-out-until-we-remove-the-opt-out thing, the coward's way to change a default.

It's not a gotcha, the article is based on a bunch of people Eliza-ing themselves on - as one person quoted within says - "…software programs doing what they are programmed to do."

Exclusive!

I wrote “I am alive” on a piece of paper, and placed it into a photocopier. What I saw next has shocking implications (science.org)

I asked it about the day after January 5th, 2021 and got a very, very terse and high-level list of points from Department of Justice court filings, which it refused to elucidate on.

Just got this, absolutely terrible.

I guess the main thing current non-Firefox users are looking for is... for UI elements to be inexplicably rounded (and for the rounded contents within them to not have appropriately-matched radii, so it all looks out of place) and for tabs to look really small (and rounded, of course) but actually the "whitespace" they've added so you can see they're rounded is still clickable? The new default theme and it's variants don't appear to have any way to revert to a solid colour, it's now an extremely distracting gradient all the way across the main toolbar.

edit: set browser.nova.enable to false in about:config

PopularBeatComboBench has been saturated

As the CEO of Terrible Ideas, I approve this take.

Writing CSS in a way that will scale up with the size of your project and team is just as hard as it's ever been, you still have to come up with a convention for doing that, including taking into account what newer features bring to the table. Having to manually edit it was never the pain point.

I work on an F100's internal, vendor/model-independent LLM chat app whose agent runs in your browser, so CLI isn't an option, direct API is out as the agent deliberately doesn't have any tools for hitting arbitrary URLs and it can't access the network via its iframe-sandboxed code execution tool, so we use MCP in the harness to let it do third-party things, with e.g. Atlassian and GitHub MCP servers pre-configured and support for BYO MCP if there are compatible third-party servers you want to use, or are running your own locally to provide tools to let it do things on your machine (it can already be given R/W access to your local filesystem via showDirectoryPicker()).

The biggest issues are usually that a third-party MCP server you're trying to use either has misconfigured CORS so the browser can't hit it, has a bespoke OAuth setup which doesn't work with @modelcontextprotocol/client, or they don't support Dynamic Client Registration (DCR) so you can't just point at it and use it. It's nice when none of these apply and it Just Works, the user can auth easily with the third-party and refresh tokens automatically handled in the background by the client.

That's the advantage, really - you didn't have to define the tools yourself, auth is handled for you, and the agent doesn't need to (and can't) access credentials or tokens as it knows nothing about MCP.

It looks like Google constantly pushing "MV3 is more secure" messaging worked at the intended high level.

Given that YouTube already has a suite of anti-adblocking checks in their UI code [1] (e.g. submit a fake request to the /player endpoint and see if anything removed the ads from it - which also tells you exactly which fields you need to remove from which request, lol), I don't know why they don't have someone looking at the latest filters and reacting to them.

Twitch did that a while back and uBlock Origin was ineffective against their video ads within a few months.

[1] https://bsky.app/profile/soitis.dev/post/3lvk7przgus2u

I have default "AI" keyword and domain filters as a separate toggleable option (so you can keep your personal filters separate) in my HN extension (which I really need to add recent model names to):

https://soitis.dev/comments-owl-for-hacker-news

I thought this was funny because they've rewritten it seemingly with the primary goal of trying to get you to not use it.

TL;DR: open app, use the app, install the app, have you opened the app yet?

I'm using this API in the internal [1] model-independent LLM chat app I work on at an F100, and it ruined using the Claude and ChatGPT web interfaces for me outside of work [2] because I'm used to being able to point the model at a folder so it can be directed to find and pull in relevant context itself, being able to add folder mid-chat and saying "you do it", and being able to have the model run code to work with local files of any size your browser can handle (every time we released a new version people would drag in their huge Excel files and go "still doesn't work" as we used to extract and context stuff the contents, but now it can poke around in them directly to find sheets/headers/structure and write code to do whatever they wanted).

Claude Opus on its own with filesystem tools built around the FileSystemDirectoryHandle API [3] makes for a pretty decent coding agent - I've been using the app to write itself live on its own development server ever since it got the ability to edit its own files, which is some of the most fun development I've done recently. I think writing your own harness is probably the most fun thing you can do with an LLM, which is why so many people do it - getting the model to add and then start using a new tool you had an idea for in the same chat is always fun.

[1] which seems like the best scenario for it in terms of the security/privacy issues it poses

[2] I ended up creating an MCP server rooted to a specific local directory - which I can expose to them via Cloudflare Tunnel - and a browser extension which adds a folder picker button to their chat interfaces, so I can get an almost-equivalent experience. This is really ugly in ChatGPT but works as well as I'm used to in Claude.

[3] as a bonus, the tools you write against this API will also be compatible with the Origin private file system (OPFS) API if you want to give your chats a virtual filesystem for the model to write to, or to copy user-attached files into

> Let's say you have a jq MCP. How do you pass data in and out to/from it without the data also being processed as tokens?

Provide a meta-tool which handles piping data in and out of any other tool, and make specific tools which can read/write data sources directly, bypassing context. Or you could go full code mode, but I'm not sure it's worth the lift unless you have Cloudflare numbers of APIs which would need tools.

I work on an internal model/vendor-independent chat app where the agent runs in the browser - every chat gets its own virtual origin private filesystem (OPFS) [1] directory where user attachments get written to and tools can read from/write to, and users can also provide read/write access to a real directory with window.showDirectoryPicker() [2] (both use the same API, so tools can route to/from either).

It can push and pull MBs of data through tools, e.g. pulling huge spreadsheets directly from SharePoint in 50,000 row chunks using a tool which calls the Excel Services REST API, passing those all into a code execution tool to join them together and process them, which generates an Excel output file using SheetJS, none of which goes into context.

People used to drag their multi-MB documents in and complain either it didn't work or the agent couldn't do anything useful with it. Now it just works.

[1] https://developer.mozilla.org/en-US/docs/Web/API/File_System...

[2] https://developer.mozilla.org/en-US/docs/Web/API/Window/show...

Nice try at trying to get me to read the friendly articles ;)

Watching it like a hawk and stopping/redirecting, or immediately reviewing and doing the same is the only way, really.

HN needs to start sticking an ?mx=1 on the end

Congratulations to the Anthropic marketing team on their acqui-hire.

I don't think it needs to specifically be a coding agent for the average user, creating apps for whatever they want to do, just something that can use code and has appropriate access for what they're already asking it to do (instead of the model bullshitting to them that it can do it, annoying them), and some way to make it repeatable when needed, like skills.

I'm currently doing something like this in the internal model-independent LLM chat app I work on at a F100, specifically targeted at our everyday users. <input type="file" webkitdirectory> lets the user give the model read and write access to a local folder (and OPFS lets us reuse the same fs tools we give the model for files manually attached to the chat, or for files tools want to create if they haven't granted folder access).

Every time we used to release a new version it was "still can't handle the 6MB Excel file I drop into it" when that was being extracted to CSV and added to context - now it can poke about in the big Excel file directly with SheetJS to pull the sheets/headers and inspect the shape of the data, and use locally sandboxed code execution to write code against either extracted data or the spreadsheet itself via SheetJS for pivot tables and such (all locally - none of which need go into the context).

The base models are good enough at tool calling (I really mean Claude, though, the GPTs just go on a tear calling tools with no context for the user) they're already decent at automating stuff for the user without a dedicated harness (our default system prompt is still "You are a helpful AI assistant", lol). Add tools for Graph API stuff, and now it can pull the nightly batch file from a support inbox, unzip the spreadsheet within, diff it against yesterday's and generate an import file for new users and draft an email to welcome them, something that used to be a daily support task (which I'd already automated most of - but now you don't need a dev for this kind of thing). Or go find the big 450,000+ row spreadsheet that's being automated somewhere on SharePoint, pull it down in 150,000 row chunks (Graph Excel REST API limit) and write code to go figure out whatever the user is asking.

Having implemented and used it, I like this setup so much it kinda ruined Claude.ai and ChatGPT.com for me, so I've hooked up similar access for them using a browser extension to add the folder picker input, with the extension talking to a local server to tell it which folder to give access to, and Claude/ChatGPT talking to the same server over MCP via a CloudFlare Tunnel to work with the selected folder.