> 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.

Upvoting because of how I misread those 2 letters

Create a new UI library without spending a decent chunk of the landing page telling the reader what it isn't challenge.

I'm a simple dev, not a storyteller, you can always tell me how would you improve it :)

Upvoting because Shorts are terrible. Flagging because the submission title - which is 100% faithful to the friendly article - is a complete lie!

Plug: I added a bunch of features to Control Panel for YouTube [1] which let you either hide Shorts completely, everywhere (which is the default) or take more control of how you use them if you do (e.g. redirecting to the normal video player)

[1] https://soitis.dev/control-panel-for-youtube

Fantastic add-on! I couldn't find an option to hide games ("playables") - did I miss it?

There seems to be a conflict with U block origin on Firefox on Android. The control panel didn't work when U block was on, even after I disabled "block ads" in the panel.

I wish they'd show up like regular videos in the subscription feed, like they used to a few years ago.

Currently, I have to guess who uploaded a short to decide if I want to watch it.

Great addon thank you

Bravo New Yorker, defeating my regular expression because I've never once seen it referred to as A.I. (I'm sure it happens)