awesome, your notes and music theory apps are very close to two of my hobby projects as well, the main difference is that my music app is guitar-centric
unfortunately, I did not have the time to pursue them. good luck to you!
You can do this in opencode and pi (haven't used), by defining your own agents or overriding the built-in ones, so in your primary agent you can disable all tools and give it good instructions for how to delegate
I imagine most harnesses should have a way to do this today, if they don't, get a new one. OpenCode i.e. is highly customizable, Claude and VS Code both support a ton as well including custom agents (though unclear if you can create custom top-level in claude-code)
Thanks, those don't deterministically prevent the main loop from using tools thought, unless I'm wrong that's just prompting the main agent on when to use specialized sub agents
you can configure tools, thinking, permissions et al on a per agent basis in the frontmatter, or via config (which they use in the examples), either location is valid, merging order (?)
the main agent would be very different, basically an orchestrator, and you are "loop engineering" it, and turning off all the things for this main agent besides being able to run subagents
For https://www.asmusictheory.com, I built in a spaced repetition test section to aid memory retention, along with "a free play" mode for when you just want to explore.
Thank you for your feedback - I have it working on iPadOS 26.5 (Chrome and Safari). The browser auto-play policy does require some interaction with the page before it will play (so the first key press is often mute, but should sound after). There is a button on the control bar to enable sound explicitly. I will look for more instances (not to ask the really obvious question, but do you have sound turned up or a bluetooth connection you're not aware of by any chance?). Thanks again
Awesome, this is a great resource. I've been working on https://www.asmusictheory.com , which focuses excercises around an interactive onscreen / midi capable keyboard (where it makes sense). I'm building it as I learn myself.
Prior to this release, Agent Kanban - the online task board with agent harness integration for task management and context capture worked primarily with Github Copilot. With this release, the extension now supports Claude Code (the VS Code extension or TUI)
I also built a kanban board with agent integration and context management, with a vs code extension to go with it (also helps with git worktrees too): https://www.agentkanban.io
There is AS Notes - an Obsidian / Logseq / Roam alternative for use a s a VS code extension (is designed for use behind corporate firewalls, git friendly): https://www.asnotes.io
AI has been a great 'exoskeleton' for me. I fortunately had some good infrastructure and solid application base templates from before AI 'got gud' and so building on these has been the best of both worlds - a solid base and improved speed of development.
The UK is still the 5th biggest economy in the world. Public infrastructure feels like it's under huge strain however, and there is also a big problem with inequality, which seems to be changing under Labour, albeit slowly.
Raw economy size can be misleading in two ways. The value of a dollar is much less or much more depending on where you're at. So an economy of 10 shekels might mean an economy of 100 widgets, or it might mean an economy of 1 widget. Purchasing power parity (PPP) attempts to account for that. The second is that economies are largely a product of population. An economy of a million making a million shekels is quite a bit different than an economy of 10 making a million shekels, so you also want to look at per capita values. Even both of these adjustments combined [1] can be extremely misleading (see: Ireland and many other places...), but they provide at least a less unreasonable basis for comparison than nominal dollars. And the UK is currently 30th there.
I think GDP per capita can also be misleading though - the GDP per capita of Luxembourg or Brunei is high, but they're such small countries that it's kind of irrelevant.
Setting aside the special cases (tiny, oil money, weird finance sectors, tax havens etc) there's basically a handful of countries which are clearly doing something right - the US, Taiwan, the north-eastern European countries (Germany, Austria, Netherlands, Belgium, Denmark, Sweden). Most of the other "developed countries" are sitting in the same sort of GDP per capita range of $65-$75k. Ranking these isn't so meaningful - the difference between the UK and France is only 1.5%.
Maybe! Our modern economic system are essentially driven by endless debt, and that only began in 1971 after the end of Bretton Woods. Even Germany has recently hopped on the debt train. Personally I not only don't think it's sustainable, and if not then it may well end up being one of the shortest lived economic experiments ever.
Something to keep in mind is that in the 70s digital tech also started to come into its own and that basically provided a massive economic boon to countries worldwide, but especially in the US. And so the concept of endless infinite exponential growth, as the current experiment effectively requires, was coincidentally paired alongside an era that made that briefly seem possible.
But now that that era is fading, the consequences of our actions are catching up to us. For instance in the US interest on the debt is now about 3% of the GDP, and the debt itself about 120% of GDP. And as faith in the debt falters, that will increase exponentially because rates for borrowing (which is how the government 'prints' money) will increase, due to reduced demand paired with increases in supply for such.
--
Basically instead of looking at GDP or whatever, I'd look to things on life contentment, optimism, and so on. If those are positive, then I think a government must be doing something right. If those are negative, then who cares what this metric or that says?
Its already speeding up human decision processes, and while ethics / alignment may seem unique to humans we also see normative expressions in monkeys or apes (like the experiment where one is given a grapes, the other cucumber).
A lot of ethics is based on symmetry: symmetric relations, equal rights, equal voting power, ... symmetries sound rather mathematical if you ask me, and decision structures have historically been pressed towards democracy (or at least depiction of it). One could say that modeling humanity as an empire with a king, ignores the will of sometimes hungry farmers with pitchforks. To prevent the occasional "implicit democracy" (royaltycide), it turned out in the interest of the king to recognize the powers of those farmers, and to formalize it in the decision making process. Or at least pretend to.
I believe machines will be able predict the preference sentient creatures would prefer in terms of decision structures, but I don't believe it will be able to predict (without human exposition) those novel preferences that stem not from sentience but from being specifically human properties (i.e. irritants which are quasi universal for humans, etc.), some of them humans know how to make predictions for (we can run expensive simulations modeling what happens when protein X is exposed to substance Y, and then make heuristic predictions of the effect on a full human in a realistic environment). So at a fundamental level I agree: machine learning models are not guaranteed to help much in predictions concerning entirely unexplored territory, neither by humans nor by natural selection. But it will definitely be capable of replacing the average human job, which doesn't involve consensual exploration outside of the homeostasis required in the implicit job description, that seems entirely automatable, regardless if its physics, mathematics, (harder than computer science), let alone programming.
It won't be able to magically systematically correctly predict out of distribution datapoints, it could only explore it like humans could by trial and error.
AI is beat thought of as an exoskeleton, you'll be at a huge advantage if you learn how to use it properly, and you will, unfortunately fall behind if you don't. I still think we're going to need people who can reason about code, and the amount of code to reason about is exploding in volume. Think of it as doctors having access to better drugs and techniques - they can can cure more illness, but the bar and expectation of what they can do will just raise. And doctors are still well paid, because what they do is important and needs doing well.
I've wondered this too - exactly how are our inputs and outputs useful as training data? So I asked Gemini. Apparently using negative sentiment in user or llm responses can serve as RLHF, and the human prompts can also serve as useful data for what problems the llms need to be able to solve. There's also that smaller models can train on and improve from data from larger models but that's less relevant when not switching models in context.
https://www.agentkanban.io - Github Copilot / Claude Code integrated Kanban board with context management
https://www.asmusictheory.com - Music Theory lessons, tools, including piano roll with midi in the web browser