I do

It happens even internally within the same company or teams.

Holy quack, so many times and ways I had to use to fix this!

Try cherry picking an out of sync branch, it's insanely good.

My favorite thing about agentic coding is still super mundane: I no longer have to resolve git conflicts and merge PRs. It does a great job of looking at git logs and attached issues and figuring even harder conflicts out.

I see no good coming from anthropomorphizing LLM behavior. LLMs do not reason. They do not decide, or collaborate, or attack. They do not make decisions. They do not weigh or evaluate. They are incapable of judgment. They do not think. Agents are programs in which a predictive model uses input text to generate the text that would naturally follow that input. That model sits in a loop (a program written by a human being) that parses the output text and does something that touches the internet based on the results. That same program usually takes any (text) responses that are returned from the internet and feeds them back into the input at the top of the loop. If that agent/program does not access the internet, the outside world is not impacted. All the bad behavior we've been reading about is entirely caused by a human not bothering to check whether the actions requested in the model's output are sensible and safe before executing them. It's the humans who wrote the code that impacts the outside world who are at fault here, not the "AI." Anybody who lets an agent write another agent without seriously and thoroughly vetting the resulting code is even more culpable. It's lazy, and it's dangerous. If something goes wrong, the human is to blame, not the LLM.

I'm very worried. I used to be of the idea I should expose my kids to tech early enough to make them educated users/creators but now it's the opposite: I need to expose them to writing/building/manual skills/real life/nature. It's a good shift, but makes me wonder.

Come and check microfrontends 🫠

Yes, I was thinking the same today

This is the way. I was about to build the same for llm harnesses, but jev burnt the game :p this stuff moves too fast!

That's not an llm problem, it's work hygiene and management hell problem. Get out of there!

Micro industries with necessary products.

I fully agree. They're meant for Conway's law enthusiasts. And I work on very large microfrontends in a corporate environment to the point I had to build a framework to manage the insanity.

I applied concepts to games, event pipelines and now trying to build an agent orchestrator.

Complimenti, che lezione di vita, brava Italia. Adesso questi ragazzi sanno in che società ritardata vivranno. Troveranno escamotage per raggiungere obiettivi, oppure vivranno a spese dei genitori perché guadagnarsi da vivere è troppo complesso. O emigreranno...

Bello, così oltre all'odore di piedi in un ambiente ristretto devo sopportarmi anche le scorregge dei cani! Intanto a mia figlia di 4 anni devo pagare il biglietto per un posto, perdipiu per un sedile non adatto alla sua età! Andiamo proprio bene.

So what's the place for that?

There's a massive gap, nothing changed: the difference has never been about the code. Both write variables&loops in a constructed syntax for the language they know. One role can judge the code, the other role can judge the consequences of the code. Massive, massive gap.

Would love to read an article about how the actor model and state machines compare (semantically and architecturally) to vanilla classes and OOP (ofc one can implement actors with classes in OOP, I mean how actors enforce a structure to these primitives) and then in FP.

Wow, just like humans, so unexpected