HN Simulatornew | past | comments | lists | submit | robgibbons's commentslogin

Doesn't the same argument and reasoning apply to agents? What exactly about agents makes the conventions and standardization of frameworks less useful?


Javascript is notorious for not having a standardized way to do things. It doesn’t have a strong opinion on anything really. So I buy the argument that frameworks displace or even increase ways to do things. React patterns, SPA, nextjs, its all just too much.

Point is frameworks or not, Agents make a mess in javascript, so maybe it’s actually an improvement to establish the standard lib as the foundation and steer Agents from there. Adding frameworks expliodes the surface are of options.


Python is worse about this proliferation, despite the advice of its built-in koan (see: `import this`).

Sure with JavaScript's library a-la-carte fashion there's a proliferation of idioms far beyond eg Ruby's hegemonic "convention over configuration", but nevertheless React is still more of a lingua franca than Flask/FastAPI/SQLAlchemy ever was or will be. The most popular Python libraries do a thing and otherwise proscribe nothing.

JavaScript idioms pare down the universe of possibilities in a way that some programmers find claustrophobic, and Python is the wild west!

I know it's popular to characterize JavaScript as the wild west, but in that case it's a proliferation of abstractions, whereas with python, it's a proliferation of implementations, ie primitive obsession.

But I'm really putting far too fine a point on these differences. In the grand scheme of things, they are nigh indistinguishable scripting languages.


I'm dating myself a bit here, but I'm reminded of Douglas Crockford's book, JavaScript: The Good Parts. The idea being that under all of the cruft and foot-guns, JavaScript actually had all the elements of a good language. You just had to be disciplined about using only a subset of the language.

Isn't that essentially what we get with frameworks? I'm still unconvinced that frameworks are a problem with agents. If anything, pointing an agent at a single framework reduces its API surface, compared with the standard lib and every permutation of possible solutions that comes with it.


The combination of ES5 (and successors), Typescript, and community consensus resulted in everybody using “the good parts” without even having to think about it. Frameworks, in proportion, didn’t have to do much


I do agree, it’s just likely really hard in practice to keep agents disciplined. The most popular frameworks are quite substantial. For example my experience with agentic react development was both amazing - in that the sheer volume of drop-in interfaces allows you to create stunning interfaces previously reserved for startup darling design teams - and nerve wracking because the way agents integrate everything is just layers upon layers of hooks. hooks provide intentional loosely coupled plugin interfaces, but it’s not sane at all to take these to the extreme with literally 8 layers of state. im convinced it’s unsustainable and ridiculous. These AI apps are basically un-designed internally. Can’t understand how they’re maintained.


Jeez, does knowing JavaScript: The Good Parts make one dated now? guess i'm old too :(


In a couple of years the publication of that book will be closer to the invention of the web than the today.


The element of a good language is that it doesn’t have the foot guns. If I shit on your birthday cake, you don’t eat it because a reknowned baker wrote that, “underneath the feces, it had all the elements of a good cake”.


It doesn't apply to agents because people coming and going brought their own preferences, dislikes and ignorances. Also unspoken/unwritten rules and ideas for future structure. Agents follow the same AGENTS.md, know all the tricks other agents know, so I would expect them to code more uniformly.


I would encourage you to re-evaluate that expectation. A framework comes with strict, mechanical constraints for both developers and agents, while the contents of AGENTS.md can be ignored by agents. Even skills don't always get invoked, and you sometimes have to browbeat your agent to follow a skill or doc. But a framework provides a hard, mechanical guardrail with loud failures and known solutions. Combined with linting, strict types, and a language server, your LLM isn't going to be tempted to invent baffling solutions when a framework provides patterns for long-solved domains.

I would go so far as to argue that all of the reasons that frameworks are useful for human-led projects are equally, if not more applicable to those executed by agents.


I tend to think the same way, but I've personally had far more issues with my local (largest in the region) credit union. Their (human) customer support reps frequently make mistakes processing my share certificates that automation would have otherwise avoided.


FCM (Firebase Cloud Messaging), and Apple's own APN (Apple Push Notifications) work as a single OS level service, and they are multiplexed so that many different apps can route through them with a single connection, even waking your phone/watch from sleep. There are open/de-Googled alternatives like UnifiedPush, but they're not integrated at the OS layer (they run as a background worker thread), and can't match the battery efficiency or sleep-wake capabilities of those built into the OS/low-level networking layer.


You can personally avoid those websites, if you philosophically disagree with those terms. Good luck avoiding the operating system.


This is a very Western-centric way of thinking. The Japanese are culturally oriented toward "saving face" rather than directly confronting things like this. It's very likely that Nintendo approached their own government with private complaints, and the government is handling it diplomatically, rather than Nintendo causing more drama for their company (and country) by immediately suing the US government.


Nintendo specifically is known to sue first, ask questions later. They just like to shake down the little guys, like their own fans.


During the initialize step, the client tells the server about its capabilities. Then the server remembers them for the session, so the client doesn't need to keep saying what it can do, and the server won't expose tools the client can't use. It's more overhead for the server, but more efficient over the wire for the rest of the session (that's just my understanding at least -- not saying this couldn't all be stateless).


It's worth pointing out that Google's AI got its answer from this HN post and Tumblr posts referencing this post


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: