gavmor

If your "opt-in platform features" and "interface to allow permissioned access to data and capabilities between different apps" is more expressive/discoverable than eg Cloud Foundry's "Service Broker" approach[0], then I am pretty excited! I run a lot of disparate services which don't interoperate except through explicit workflow automation pipelines (I use ConcourseCI to eg upload images to Immich [1] albums, but others might use n8n[2] for the same purpose).

The "workflow automation" approach is a lot of resource overhead and broker-config maintainance, but my kingdom to be able to arbitrarily compose apps' states, eg commutimemap.com + Craigslist.

0. https://www.cloudfoundry.org/technology/open-service-broker-...

1. https://github.com/gavmor/immich-concourse-resource

2. n8n.io

What's the transition threshold at which paying down tech debt becomes worthwhile? Maybe it's a gradient.

I believe the conspiracy was real, but was itself an emergent manifestation of the conspiracy hunters' paranoia.

As the occultist Agliè explicitly champions, "in its loftiest sense syncretism is the acknowledgment that a single Tradition runs through and nurtures all religion, all learning, all philosophy". He asserts that "true esotericism does not fear contradiction".

None of what was published could falsify the syncretic paranoia-therefore whatever existed was the cult, since no tradition could be excluded.

My agent didn't like it. Indirection causing noise and failure outweighed the token savings.

https://regular-reviews.pages.dev/rtk

Oh, of course. Brilliant.

I'm thinking more in terms of the case where my coworkers' agents aren't working via graft, and changes are made without the post-edit update hooks.

Is this still cheaper when stale?

I don't know anything about investing, but I know a lot about naivete. :)

Or is it just an unproven attempt? Seems like a pretty straightforward value proposition. Caveat emptor.

It takes place on another planet, and isn't alien biology "science" speculation, enough?

Besides, it's not even her best work.

Looking forward to reading your story! You might consider Ted Chiang.

I like setting arbitrary project milestones or timelines. They don't have to kill the project, but it's good to cast efforts in relief against external developments.

My daily driver is Agent of Empires (https://github.com/agent-of-empires/agent-of-empires)

I just started experimenting with GSX and GSXUI

https://github.com/gsxhq/gsxui

https://github.com/jackielii/structpages is what I might call a framework that GSX sits nicely in.

Also one ai haven't tried: Templ.

https://github.com/a-h/templ

"DRY" and "KISS" are, possibly, the least interesting principles to which a software designer might adhere.

I'm sure it already can with the right mod/plugin.

I've got an application for this. Will try and get some benchmarks in the next few weeks. We're definitely attempting to converge on a quality inference without wasting tokens/time.

For now, we're passing the first pass to the humans, and that's roughly 80 for 20, but to get the last 20 without blowing up our token spend? This might be the approach.

Thanks for the write up comment, btw.

The artwork "as it was created" is unavailable. The only options are Rougeoux or the ravages of time.

A regular LLM acts as a "policy," mapping a current state to a specific action (states → actions). Their new LLM acts as a "world model," mapping a current state and a chosen action to a predicted future state ((states, actions) → subsequent states). Instead of deciding "what to do," its explicit objective is to predict the exact environment observation that will result from the interaction history and the agent's current action.

I assumed at first that it was trained on synthetic data, but they actually went and deployed real physical hosts and virtual machines (e.g. Ubuntu, macOS, and Android) and browsers. They ran agentic systems on these continuously and recorded the actual, real-world interactions.

So it's an LLM that infers next state, or outcome,as structured data e.g. literal HTML code, UI view hierarchies, or accessibility trees.

The cold takes themselves are a fantastic proof of the care and attention the devs put into this game, as well as the depths of their design philosophy.

> Almost nobody optimizes compiled assembly code.

Compiled assembly code is not an input to the next compilation; source code is an input to the LLM's next inference.

Sure, maybe "prompts are the code," but you must realize that code is also the prompt.

Well sooner or later I would expect a developer who intimately understands their code base to feel compelled to start refactoring and extracting fitting, meaningful well-leveraged abstractions.

Migrating to a workerd container is an option.

What's the data doing that's so sluggish? Is it being correlated/transformed, or is it just so many points of light are blocking each frame?

I wonder if Mollweide or Atlantis projections wouldn't be more performant?

Riding horseback saves time over walking but it's harder to smell the roses along the way. Nevertheless, millions now ride horses recreationally.

Who gets a sense of accomplishment from cheering for their home team?

The overall system that allowed this implementation is accountable. So why put such a fine point on it so as to exculpate the LLM?

> He was the perfect protagonist for a teenage boy: a coward, an underachiever, technically a wizard but only on a technicality, and frequently the most powerful spell in the universe was lodged in his head against his will. This will be familiar to anyone who has been sixteen.

s/frequently/initially

Also, how is a cowardly underachiever "the perfect protagonist for a teenage boy"?

"technically a wizard but only on a technicality" is obviously redundant

And what part of any of this is supposed to be familiar?

It's just a strange essay.

That's sorta how Agent of Empires and also Zed seem to operate—worktrees as a first class aspect of the workflow.

Give credit where credit is due: Descartes, Kant, Putnam, etc.