Haven't built anything on the agent skills platform yet, but it's pretty cool imo.
On Android the sandbox loads an index.html into a WebView, with standardized string I/O to the harness via some window properties. You can even return a rendered HTML page.
Definitely hacked together, but feels like an indication of what an edge compute agentic sandbox might look like in future.
It's not that the context window is adequate, but rather an agentic LLM can search the source of truth using appropriate tools (SQL, term search, etc.)
RAG made sense when the semantic search was based on human input and happening as a workflow step before populating context. Now it happens inside the agentic loop and the LLM already implicitly has the semantics of the user input.
Living here the decline is tangible. And this is West Oxfordshire; not one of the poorer parts of the country.
An example in microcosm: a local village suffered road flooding due to failed maintenance of water pipes. Our rent-seeking privatized water company effected the minimum repair required by regulation.
The next section of old pipe burst almost immediately, flooding the road further for most of January, utterly destroying the surface, through the road base in many places. Even at a crawl it's difficult to avoid tyre damage.
Over a month later the water repairs were effected. Then shortly after some local roadwork notification signs were put up.
Those expecting repairs to the moonscaped road were disappointed: instead the relentless bureaucracy of British local government installed traffic calming measures on top of the broken road, as the work had already been booked and could not be stopped by any means as even basic roadworks lack any degree of dynamism in their execution.
All this still needs to be made right. These small scale failures will compound and compound until the entire state is drowned in the consequence of its incompetence.
Having seen a family member die absolutely horrifically in a matter of weeks due to late-diagnosed pancreatic cancer, I'd consider suicide if I got the same diagnosis.
Always wondered if dreaming is some kind of daily memory consolidation function. Logged short-term/episodic memory being filtered and the important bits baked by replaying in a limited simulacrum.
I'm copacetic to the notion we're not at enterprise codebase level (yet), but everyone who still thinks agentic coding stops at React CRUD apps needs to update their priors.
I needed a poc RAG pipeline to demo concepts to other teams. Built and tested this over the weekend, exclusively with Claude Code and a little OpenCode. Mix of mobile app and breaking out Android terminal to allow Sonnet 4.5 to run the dotnet build chain on tricky compilation issues.
I still manually approve tool use requests at the start of a run. As it gets deeper in I might allow it to run safer commands without that oversight (e.g. writing to local text files), but potentially destructive execution still requires approval.
As for the local env, I'm treating the Android terminal as a sandbox. Anything gets trashed I just reset and reinstall my toolchain.
I won't pretend I'd use this workflow for anything high-stakes. But for simple things like "I wonder how my Hue lights actually work?", its viable.
Possibly Codex, but I've only used Claude Code so far.
Worth pointing out I'm not SSHing to a different device. Claude Code installed and running directly in Android terminal on my phone.
I've built ASP.NET Core APIs on-device this way. Install dotnet in the terminal and Claude can write code, build, run unit tests, and even run the API on localhost. Then use `git` and `gh` to commit, push and raise a PR.
This is how I do mobile device coding. Android terminal w. git and gh installed and authenticated. Claude manages the feature branching and PR process; I review the PR in the GitHub mobile app.
I'm using the Android terminal and Claude Code to vibecode on the go. Or rather, as a fairly boring father of two, when I'm tied up in the necessary chores of family life - cooking and cleaning. Nothing as complicated as this - just Claude Code and a fairly standard Linux dev term, but it's remarkable.
Over the recent break, across four or five sessions, I wrote a set of prompts around ~500 words in total.
The result was Claude scanning my network for active ports using nmap, fuzzing those ports with cURL, documenting its findings, self-directing web searches for API/SDK docs for my Hue bridge and ancient Samsung TV, then building a set of scripts to control my lighting system and a fully functional HTML+JS remote for my TV.
The most entertaining part was Claude prompting _me_ to pop into the living room and press the button on the Hue bridge so it could fetch an API key.
The most valuable part? The understanding I gained secondary to generative act. I now understand the button on a Hue bridge literally just tells the device to issue a new API key at the next request. I understand how Entertainment mode works, and why. I understand how Samsung SmartThings is mediated via websockets - and just how insecure decade old Samsung TVs are.
Around 500 words to gain all this? I hate to buy into the hype, but it feels inflectional.
Wow, that's brilliant. Can't help but think your script unlocked this. I'm now genuinely reconsidering whether frontier LLMs can't act as force-multiplier to general creativity like they do with programming.
Whitehall - the UK civil service - persists between governments in a fairly unique way. It's essentially a political entity that exists beyond democracy that has pinky-promised to be politically ambivalent.
To paraphrase an adage I've forgotten: you can skim as much shit as you like off the Thames, it'll still be a filthy river.
I'm confident you could build one of these in an IF engine like Inform, but the offering is fundamentally different. These books are essentially compressed TRPG experiences where the gamemaster's actions are encoded into the "go-to page n" directives.
On Android the sandbox loads an index.html into a WebView, with standardized string I/O to the harness via some window properties. You can even return a rendered HTML page.
Definitely hacked together, but feels like an indication of what an edge compute agentic sandbox might look like in future.