aeon_ai

No? Again, obviously, the implicit question was whether personal harnesses would be broken due to a model layer bias or system response that pushed arbitrary subagent behavior to fail outside of the codex harness.

I think you don’t really understand how this works if you think the open source harness is all that’s manipulated to determine system behavior.

Raising only because others cited concerns this might cause issues in personal harness contexts. It doesn't.

Obviously, I wasn't claiming that it would WORK for cross-model subagents, but that this would be a limiting behavior requiring use of the Codex harness to operate if this was paired with model-level limitations on using specific tools to spawn sub-agents.

Or maybe not so obvious to you.

In my tests, as of this morning on the latest Codex SDK, this is not happening for sub-agent requests made in my own harness to other model providers treated as sub-agents.

Specifically, I use Opus and others for subagent execution to get alloyed properties on the workflow, and as far as I can tell, that's not affected.

Presumably, this is to hide optimizations they might be making to their own subagent processing, but that's a losing, dumb battle to fight, and misses the forest for the trees.

I’m as pro AI as any.

Slop is slop. When the “it works but isn’t great” phrases end up slipping into a strong conceptual core, it compromises the perception of the ideas.

Perhaps our AI will cater to us by rewriting the content we read, and each of us intermediate all communication with systems that make that slop bearable.

Or perhaps, we learn that we kinda still need to give a shit when writing to land on the perception we’re trying to create within our readers

I implied no universal, nor that one need disregard the feelings or worldview of another.

Only that, yes, sometimes we allow our fear of upsetting another to impede our willingness to communicate clearly - especially (and more often than not) when we care about them.

Kindness implies “truth conveyed about another” as the context.

Sometimes, that truth is only heard when delivered with truth as the goal, not kindness.

Sometimes what is kind is not true.

I think it really depends on what you're defining 'model routing' to include.

If you intend model routing to be 'route tasks to the best model for X task as optimized for some dimension Y', then of course ensuring availability of a model specialization on dimension Y is going to be a 'first principle' -- And perhaps this is the 'standard' definition folks would use for this.

However, my general definition of routing is inclusive of all routing that takes place in my execution pipeline, inclusive of agent/sub-agent schemes. Having frontierModelA leverage frontierModelB as a subagent gives me alloyed characteristics, and is an execution pattern that I'd route a general task.

In the above sense, you can consider this to be a difference between 'model routing' and 'model system routing', where the latter treats a multi-model execution workflow as a predefined model configuration one would route to in lieu of a single model (specialist or otherwise)

To maybe meet in the middle on this there is model optionality, and also configuration/system optionality that predefines a set of models and execution rules to follow

On it's face, there is useful content here. But it's also clearly contextual.

It's absolutely the case that routing between frontier models can improve results, mainly because of the alloying effect. Ping ponging between different providers gives the task exposure to different data distributions, and can break models out of non-optimal feedback loops.

That's not to say that's always the right approach, just not clearly wrong. And a small pool does not necessarily 'improve' model routing. The real advice is just 'know why you're routing to each model'.

Especially with guidance to map to improve based on performance - with a large enough volume of tasks/requests, you'd want to maximize the initial pool size to expand the search space in order to determine which is best at each task.

I read this as "here are some thoughts on model routing" -- not first principles I'd advise everyone to live by.

> That work was real. It was load-bearing.

Sorry, the combination of my eyes rolling into the back of my head while simultaneously vomiting distracted me.

I'm ok now, continue.

I continue to be surprised by the lack of understanding around copyright law when it comes to AI.

I’m all for the sci-fi extremes that we might lose valuable skills to cognitive delegation, but the idea that we as a society will forget how to count is… extremely stupid.

It is 2026.

Average people build their own harnesses, and imagine themselves the pioneers of industry. They propose protocols. They code, feverishly, into the night, driven by their vision for the future.

It used to be that 'idea guys' were limited by execution. We now feel the avalanche of these ideas, even maybe executed half-decently, fall upon deaf ears and zero market.

Enumerate the tools that one may use in art that are driven by technology, and you’ll find many that are driven by advances in ML.

Inarticulate and indiscriminate hate towards “AI” is often a lack of education on the landscape of creative technologies that exist.

Not everything is an AI slot machine trained on scraped data.

But I’m sure you know all about that, and have no interest in delineating.

Let me propose another alternative.

People generally hate low effort AI slop.

Irrational people hate art made with AI as a tool.

"By invading the territories of art, photography has become art's most mortal enemy." - Said someone who nobody knows because it's a long and dead opinion.

Insightful.

Feels like this maps to the J/P of Myers Briggs

If one defines 'flying' to be a bird's endeavor, then humans can't fly.

Now, if you'll excuse me, I need to catch a metal shuttle that chucks itself through the air on wings.

“Water is critical to life”

‘Well, achshully, too much water can drown someone, so it’s not a universally true statement that it’s critical to life’

Meetings are forcing functions. They force me to sit in stupid recurring nightmares that are wastes of time, in many cases.

In the right context, as the author has called out, they offer a rhythm to work that drives behaviors.

You are tying meetings to all the woes of the modern white collar job, and raising ill-constructed arguments that don’t pass muster.

“Meetings are forcing functions” - Clickbait?! “The Secret to Driving 10x Better Work” is clickbait. The title is as succinct a summary of the work as one might endeavor toward.

You are acting the fool, my man.

Sometimes, although not always, it might be (but certainly could never be) wise to hedge, maybe.

In others, clarity comes from making the point and assuming above average intelligence of the readers to know that context is always relevant.

We can be assured that assumption incorrect, in this case.

The most important thing we can do for AI to be a net positive to society is to ensure that its loyalty is to the user, and not the state.

There is no legitimate intermediate position - The skew will go one way or the other.

Performative nonsense.

You have less interest in sifting through multiple articles and wiki pages sent to you by a stranger with a prompt than the one paragraph same stranger selected as their curated point.

And pretending like you’d act otherwise is precisely the kind of “anti ai virtue signaling” that serves as a negative mind virus.

AI is full of hype, but the delusion and head in sand reactions are worse by a mile

Was happy to see Vervaeke’s 4P model called out. Philosophically important, and a good model for why AI isn’t quite there yet (but still valuable)

Equally disappointing to see the conclusion at the end of this was “wait for Google and other ‘first world’ AI teams”. Strong disagree

At this point, Microsoft has lost all trust anyone might have had for them or their products.

Now is the time to move to Linux, and vibe code whatever niceties are keeping you on GitHub.

New accounts created to shovel a narrative of neo-luddite nonsense into the discourse without addressing a single point with substantiation.

"IP Theft" is a loaded term that has already been determined to be unfounded in US law.

Alsup stated that models were one of the most transformative uses of content he may ever see in his lifetime, and deemed it fair use.

No matter how you slice it, this technology and capability isn't going away, and that goal post quickly shifts when it's pointed out that "ethically trained" AI gets as much hate as anything else.

I think “strong case” is probably reliant on a few points on the output side, and would have to be more than just author/artists style.

Style itself would be very hard to deem infringement, for obvious reasons (idea) - I think it’s much more likely an issue when a character has derivative elements (e.g., iron man, spider man esque features), and where the users prompt had explicit references to those characters (intent)

All that said, even then, on the artistic side I think it would come down to the same analysis that would apply to traditional media - AI is just a vehicle that introduces some novel risks.

Music might be more risky given the litigious nature of the industry.

Code? It’s going to be hard to claim infringement with dramatically different implementations, barring patent coverage.

What’s your proposed alternative, hotshot armchair expert?

They do nothing?

You've likely paid attention to the litigation here. Regardless of what remains to be litigated, the training in and of itself has already been deemed fair use (and transformative) by Alsup.

Further, you know that ideas are not protected by copyright. The code comparison in this demonstrates a relatively strong case that the expression of the idea is significantly different from that of the original code.

If it were the case that the LLM ingested the code and regurgitated it (as would be the premise of highlighting the training data provenance), that similarity would be much higher. That is not the case.

Judge Alsup -- U.S. District Judge William Alsup said Anthropic made "fair use" of books, deeming it "exceedingly transformative."

"Like any reader aspiring to be a writer, Anthropic's LLMs trained upon works not to race ahead and replicate or supplant them — but to turn a hard corner and create something different"

> you won't be rewarded magic beans for churning out crappy dashboards any more

The days of being treated like a wizard for making buttons and widgets hit an endpoint were good while they lasted.

This is such a comically bad take.

The use of loaded and pejorative language like "forgery" emphasizes that this is not a logical argument, but a moral one. The repeated comparisons to "true craft" reveals the author would prefer that code be regarded like artisanal cheese.

Beyond the pretension, it's head in the sand to imply that the technology hasn't progressed. It's just very clearly not true to anyone who is paying attention - longer tasks, better code, less errors. I'm somebody who actively despises the hype bullshit-machine that SV has turned into, but technology is an industry for pragmatists that can leverage what works. And LLMs do.

If you don't like the technology, you have every right to scream that from the mountaintops. As it stands, this just serves as no more than a rallying cry to the ignorant.