Complete aside, but it's beyond infuriating I need to enable a VPN here in the UK to view this link.

It's ironic because it looks like a picture of a dilapidated 2000s "millennium park" type of location which are common in the UK.

> Complete aside, but it's beyond infuriating I need to enable a VPN here in the UK to view this link.

Here, I uploaded the image to catbox.moe if anyone's interested.

https://files.catbox.moe/c4smhd.png

I don't think that catbox is blocked within the UK.

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.

Yes I (sadly) know. I commiserate with your loss.

Still wouldn't let my loved ones try untested treatments though, especially if it buys only weeks of extra lifetime. The potential costs are too high.

I wonder what training insights could be gained by having proven general intelligences actively navigate a generative world model?

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.

There was once a neural network that used dreaming phases for regularisation. It would run in reverse on random data and whatever activated was down–weighted.

That's the wake sleep algorithm for undirected graphical models.

Hinton had a course on Coursera around 2015 that covered a lot of pre NN deep learning. Sadly I don't think it's up anymore.

There is this with a 2012 date:

https://www.youtube.com/playlist?list=PLoRl3Ht4JOcdU872GhiYW...

> a poc RAG pipeline

Why would that be any harder than a React app? At least for me having an LMM produce a decent and consistent UI layout is not that straightforward

Not sure why you’re getting downvoted, but that’s exactly what AI is turning out great for.. being able to make something in a weekend that would’ve taken weeks otherwise means other things downstream of it suddenly also become possible.

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.

I read the Readme. So this is all just stuff you can do with Claude's cli interface? It edits files and runs utilities? And it does this with few enough errors that you can be productive by just chatting with it over ssh? Is Claude the only one that can do this?

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.

Probably Claude Code and Codex are the currently best ones, Claude Code a bit faster, Codex a lot more precise and "engineering" focused.

As long as you figure out how to verify that the built thing actually does what it's supposed to, ideally with automated tests, it's almost fire-and-forget if you're good at explaining what you want and need.

How did you make sure Claude wasn't doing anything unintended while allowing it to run scripts it wrote on your network?

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.

Run it inside a VM, make snapshots of the VM if needed (or use vagrant/ansible to rebuild), commit regularly, ...

The VM still needs access to the network for the use cases they described though.

That seems incompatible with the parallel tasks of cleaning and cooking (at least for me, especially with kids around).

The VM is setup once, before you get to be "on the go": that's your development environment, you need one anyway

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.

thanks! here's the script for reference: https://github.com/vtomnet/hn35/blob/main/generate.py

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.

an adage that is certainly true in the analogy but no longer true of the Thames.

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.