Gold based money, or eras of coinage, historically have been times of war and slavery. The debt system we are in now is far better in a lot of ways. The outcome of what happens depends on the political will deciding where the credit flows.
Or it could be that they want to give people they don't know the benefit of the doubt. I don't really consider it a sign of good character to not do this and the vast majority of people would too. That you didn't even consider it...
James Damore was a poorly educated person. He didn't understand how to use statistics and decided to use them in a hateful way. Just because numbers are involved doesn't make a viewpoint objective.
Creating a hostile workspace for others is not a smart move.
I think there's a lot more political will now than there was a decade ago for explicitly repealing the sections of American civil rights law that define what a "hostile workplace" is, in order to make sure that something like Damore's memo would not count. Certainly, this is something I think about when evaluating political candidates.
What are the major historical examples where protecting employees from a "hostile workplace" is important? Racism? Misogyny? Homophobia? Do protection from these things look expendable to you?
I'm sure either of us could quickly find a bunch of people who would like to one or several of those acceptable again, yet us finding that such people exist would not tell us a damned thing about whether dismantling those protections is a good idea. Or supposing it does, then one might even make the case that those people existing is an excellent reason for having such a law in the first place.
Wow, this takes me back of making my own software renderer and game engine as a teen in the 90s. Then OpenGL came out and fixed pipelines and some of the cool magic of doing anything with pixels disappeared (until pixel shaders came back). One cool rendering technique you don't see much today is voxel graphics.
As someone who has been a startup founder across several and who has basically been under-paid for the last decade as a result I am constantly thinking if I should have went to work at big tech again as many of my peers are much richer for doing it.
But Paul Graham is right, you weren't meant to have a boss. In fact this is not unique to programmers either. Nobody is meant to have a boss.
I encourage everyone to read "The Dawn of Everything" by David Wengrow and David Graeber to understand the kinds of human organizational structures that are possible and have existed in the past.
I might be biased because I came up with it, but we are over complicating these systems. There is a simpler way, and it appears to work well since I built a system using it to test the idea.
- I think the comparison to TCP/DNS/BGP is the more apt one compared to MCP/A2A
- Those protocols negotiate capabilities and exchange information about themselves, but not in a self-serving manner of just talking about themselves, but with the goal of ultimately transporting data for a higher layer. Ask Protocol lacks that.
- Objects don't exist in a vacuum, but in a context. As the objects will only know about themselves they will always be limited in how to describe themselves best. An LLM that lives on the outside and just gets a static description of an object will be in a much better description to answer an "ask" query.
- Given that the existing agent protocols you are putting it in a context in already come with "description" fields and the like, the protocol seems too little of a value add to actually target. e.g. there is no benefit for a MCP server to conform to the prescribed manifest rather than implementing a freeform "ask" tool.
- If you want to actually bring the point across that it "occupies a different position" than transport/agent protocols, don't put it into a comparison matrix where you force it into the same schema
The reason comparing to TCP, DNS doesn't make sense is this doesn't replace those at all. The reason I compared against other agent frameworks and things like MCP is because that's the common question people have.
You are right objects don't exist in a vacuum but you are wrong an object that just exposes a description and an LLM reading it from the outside does better. Think about object oriented programming, objects expose and interface but don't reveal all of their internals. Calling the Ask handler could change internal state. Maybe response depends on what object is asking. Maybe the Ask handler might want to call the callers Ask handler too. You can't do that by just exposing a description.
You said the goal is to ultimately transport data to a higher layer. That's not the goal. You are thinking too hierarchical. The relationships between objects is dynamic and the concept of a higher layer makes no sense here since the point is to get rid of the hierarchical nature current agent protocols have.
Keep in mind I built a working system to test the concept. You can download and try it.
Companies are spending about $1 trillion this year in capex in the US! World wide estimate is about $2.52 trillion in AI spend in 2026 according to Gartner. There has never been a bigger spend in tech. It's so much spend that the software industry has to basically double in revenue in the next couple years to keep up.
Most of that spend is on infrastructure, GPUs, ASICS, and everything else that goes into a datacenter.
https://youtu.be/DNCZHAQnfGU?is=CWQS-QUJB0z4EfSM
reply