Reallocating human time is also going to cause problems.
But it’s a great short term business opportunity for AI vendors and it was Anthropic who went all in on being knowledge worker outsourcing in a big way first whilst OpenAI thought they’d replace Google in search.
I think Anthropic had the better business strategy.
We can have a philosophical debate about work, the history of work and its relationship to human psychology in the 21st century but the bottom line is that there are 8+ billion people on the planet and, of those who are "working age", the vast majority of people, lacking meaningful capital, can only secure income by selling their time and labor.
There's absolutely no evidence that if we come up with a way to "reallocate human time" and change the structure of our civilization (using AI of course) tomorrow, the masses would benefit. There's plenty of evidence that the people who control AI or have the capital to employ it will use it to accumulate as much power and wealth for themselves as they can.
> the vast majority of people, lacking meaningful capital, can only secure income by selling their time and labor
It's just time and it's the only things humans value. The only way to provide value for another person is to use your time to do something faster than they could do it with their time. That's it. There is no other way to secure income outside of inheritance or charity which is just receiving something of value without giving something of value. There's a reason why most of the income goes to older people, because the younger people haven't accumulated that much time to exchange for money. The nice thing about time is that everyone earns it at the same rate, 1 second per second.
Capital can be a lot of things, not just machines and property. Any experience you have is capital, any training is capital, any education is capital. Capital is anything makes accomplishing things take less time.
The difference between socialism and capitalism is the idea that one person's time can have different value. That's really it.
For the Capitalist crowd, YES it is the biggest cost. The next is energy. Imagine a world where your research and development is all AI and the production is all automated by robots. Instant product to sell to the masses who has no money because no one is working.
In the future a few thousand billionaire geniuses will own a world of unimaginable luxury and near-infinite longevity. They will make the decisions, AI will execute them, and robots will do the physical work.
Everyone else will be reduced to compost.
It's the perfect plan. The final definitive justification for capitalism.
The masses are unnecessary. The masses will be optimised.
Why do billionaires keep working, keep amassing more money, donate to politicians, buy media companies?
They want influence and power. Being at the top of a hierarchy of millions, billions of people.
If there are no massess the 1000th billionaire will be a the bottom of the hierarchy instead of near the top. They don't want that. The masses are needed to give them the sense of power.
What these people want is power and control. Eliminating the masses goes against that.
I don’t think that’s it. I think the only thing that motivates billionaire is just to have more than the next guy.
The only thing that motivates Bezos is that Elon Musk’s has more and conversely Elon Musk would have a existential crisis if he was no longer number one
I feel like one mental model here is that the attention is limited and under capitalism capital aggregates in the hands of few. Their attention is limited to things that immediately better their position, the most capital-efficient thing to do is to gather more capital.
Cheaper prices, affordable housing, affordable healthcare are less capital-efficient. If you're Walmart, sure, you would like to lower prices as much as possible. But your leverage really isn't as big as finance or tech. If you're a politician, you might also pursue those goals, but your attention and leverage really isn't as focused as that of the money machine.
this is true of most actual clouds/neoclouds. oversubscription and intelligent placement of workloads is already something they do. I’ve known a few people at AWS who have offset unbelievable amounts of cost by optimizing placement.
I am pretty excited. The factuality of important events has been distorted for most of history. Moving to a low information trust society is something that I think will be positive.
I don’t see it leading anywhere but a flat earth. When no one can be trusted whoever can tell you want to hear will be who people listen to and snake oil salesmen will reign supreme. Even if he was CIA, Cronkite’s world was closer to the truth than Alex Jones’.
One of my professors at Uni a year ago was arguing that due to genAI we would have a shift of trust into established institutions/people, so government (I'm not American so I don't know if this is possible after many recent scandals for example), Universities, people with authority/knowledge, close family members that are trust worthy, knowledgeable and/or work in before mentioned institutions. So basically we would revert to pre-web times where we had to trust some entities whenever we liked it or not.
I personally worry that what that would mean is we are left with little to no institutions to trust, besides Universities and family members, I don't think I would be able to trust governments and corporations, but I guess before internet people also weren't blindly trusting those.
I doubt the new trust bearers will be anything like governments and universities because trust in them has been severely eroded. Sadly, they will be select Youtubers and Internet influencers.
I've lived in a low information trust society and this was not the outcome at all. People trusted their local cliques much more, and there were local minima (e.g. a mainstreamish political party with leaders that are actively and dangerously anti semitic), but in general people were way more willing to engage with ideas.
One implication was people were more social and talked about ideas more. Thought had not been outsourced to arbiters in the way that it was in the U.S. People with authority, knowledge, and close family members were definitely inputs into what people thought, but by-and-large people still came to their own conclusions.
You got to see the gradient of thought that people actually had about issues. People would say their insane ideas out loud. You could disagree with people and have them actually engage with your perception of reality.
This is kinda cute because it glosses over the lack of critical thinking skills, lack of research skills, and willingness to believe magic bullets, which would make most of us believe nothing of substance and yet fall for anyone with a silver tongue. Heck, we’re already dangerously close to that without LLMs.
Low trust societies are poorer because everyone has to spend much more effort on verifying everything. People give up business opportunities because they can't trust their partners. It becomes more nepotistic because people trust family over strangers.
Low information trust societies get destroyed by pandemics of both physical viruses (due to anti-vax and medical distrust; we can see this happening again with Ebola) and destructive memetic lies (see 20th century fascism).
I've lived in low information trust societies, and they were much intellectually healthier than high trust societies, at least in the white collar communities I was in.
Moving there, I was shocked at how "conspiratorial" everybody seemed about everything. Living there, I was shocked out how often they were right. But it didn't impact people's likelihood to do things. I think they are actually orthogonal in a way that is unintuitive.
Ignore the naysayers, they are just jealous. You got it totally tight, not everyone get's it like we do. We are facing alot of backlash for our beliefs these days.
Listen, I'm hosting this Telegram channel for people like us, where we can exchange free information without media bias, share the real facts and plan coordinated activities against these poisoning mainstream scumbags.
I also have a 20% coupon code for Wamp® Wolf-Testosteron for you, Wamp® really helped me stay awake and alert in these dire times.
But this is exactly my point -- in a low information trust society things like this our noise. They work in high information trust societies because who would sell medical products that don't work? A doctor is leading Wamp®, surely a doctor would never lie to us for money?
In low information trust society everything is noise except what passes a smoke-test or who you believe, which plays on this general tendency of humans to prefer comfort over challenge, confirmation over rejection.
A high information trust society has regulation in place which tracks such acts of manipulation so that this trust is not abused (e.g. regulation against misleading/false advertising).
A low information society promotes the notion that everyone is lying anyway and everyone is on his own to figure out what's true. So regulation gets dismantled, and the premise becomes "it's not lying if I can make enough people believe it".
> I don’t think you have ever actually lived in one.
I lived in societies of high and low information trust, and observed first-hand what happens on transition. If trust in public information is high, people contribute and challenge common sources of information, and there is high expectation and punishment to rectify, improving the quality and transparency of commonly agreed information.
In low trust environments, people start to distrust everything, initially seek out explanations but then largely gravitate towards information sources which confirm their assumptions or own bias, because they lack time, energy and skills for any other path. To stabilize themselves, they then build a mental "fortress" around their belief which is periodically fostered not by challenging it but by seeking out others who confirm it.
Advancing in this direction increases the general consensus that there is no common ground (because this requires common trust in some information source), it gets increasingly difficult to educate such fractured groups, because there is no longer a path for many to accept inconvenient truth in light of a more convenient "alternative truth".
This is poisonous in a democracy, because common agreement on facts is what's so crucial for this process.
Hence my learning that it's not a healthy direction for a society (and also the reason why systems attacking democracies don't aim to gain trust, they build distrust)
> but the most ideologically open cultures I’ve seen are LIT.
There is a huge difference between a ideologically open society and a low information trust society. Accepting other ideologies requires trust.
A low information trust society breaks down trust not just in institutions but also among citizens, which is the fertile ground for polarization and actively prevents open ideology.
You may have the wrong understanding of the terminology. A high-information-trust society doesn't mean that everyone blindly accepts a leader, it describes a system where trust is maintained. In a functioning democracy this happens because society constantly challenges institutions, as it DEMANDS to be able to trust them.
In low-information-trust systems, the consensus is that no one can be trusted. So no joint effort is taken to hold power accountable, everyone plays to his own fraction which erodes common grounds, solidarity and citizen power.
Declarative approaches require validation to live at a synthesis layer, while an imperative approach that compiles down to declarative configs at runtime gives you the best of both worlds -- this is why anyone who does not need terraform cross compatibility will write things against CDK or Pulumi that has the same declarative schema wins with the niceness of testability and author-time typing.
Edit:
That said, it is shockingly close to the schema that we wound up with with a few ideas that I think are interesting.
reportsTo allows bottoms up orchestrator delegation
workspaces are interesting -- right now we have one bag of data with per-subagent data subscriptions, but this means that we frequently add input requirements to subagents that really should be more implicit
accessPolicy seems like a footgun to me -- i feel fairly convicted that tools should define their access scope and the only thing a subagent should know is the bag of tools available to it.
human approval seems redundant given we already have input requirements, and one can just be `email_approved` with a tool that emits the human approval request and `email_approved | email_not_approved` -- same feeling about `GateTypes` in general. If we are working on flat input-output requirements, then why do we need a specific GateType handler?
Trigger `any_approved | all_approved` is going to bite you if you move into plan solving. It is not rich enough to express XOR style relationships and I am willing to bet that v2 of your implementation splits TriggerRequirements where TriggerRequirements can be recursively applied to the type.
It seems like the tool definition is missing a lot of niceties that have been important for us -- for instance, at most once invocation. But we are working primarily over voice where there is a strong need to control execution for quality of service.
What do you mean by "Terraform cross compatibility"? Pulumi was (initially) built upon the same underlying providers so had the same capabilities.
I'd posit the main difference between the two was Terraform's declarative approach provided more consistency and predictability in how infrastructure was defined and provisioned. The constraints it imposed were the benefit vs a sprawling estate with a hundred different bespoke ways to provision a given service in your preferred language.
On accessPolicy — sub-agents in Envelope are the tools: each defines its own access scope, the supervisor just knows what's available. Where the concern is valid is function-level tool calls — no first-class tool definition layer yet, so HTTP access scope ends up at the agent level rather than the tool.
On gates — the per-record model handles dynamic output you can't pre-declare at schema time, and timeout/onReject are runtime routing decisions. The action type specifically is doing real work — irreversible step, explicit approval required before it fires.
On trigger logic: agreed. XOR isn't expressible with the current set and recursive conditions is almost certainly the v2 shape.
Read some of your other stuff. I think we're on the same track, which is interesting! Everyone in our (admittedly SF centric) circles is trying to chase this down from the model path rather than building the consistent execution layer that we believe all of these solutions will need.
Thanks, good to know we're on the same path. The bet is that sub agents will work together in teams, and different models will be better suited to different sub agents/tasks. At that point, coordination, observability, and governance are best kept vendor agnostic. Same to you!
this is bad. Anyone doing any cursory work with agents will realize how brittle <<just managing your own prompts>> can be. Adding an extra layer of indirection isn’t helpful, it’s a gigantic hindrance that gives you a moving eval target. Being an MCP developer means you have a moving target of model optimization. It is a win for nobody.
The tools we need to solve this problem exist and they are boring. Types, jsonschema, openapi, all of it is a better integration point than MCP.
For those of us who lived this wild arc from the advent of normative protocols widely adopted, standards, open source, and the variety of “paradigm shifts” over the last several decades it’s not surprising to see a profusion of attempts at standards with poor adherence across tooling, and fits and starts along the way. Those using the modern web, but not old enough to have built it, which has largely calmed down, probably look about them at the relative order of things and sigh in contentment then squint at the AI agent standards and huff at the confusion. Those few other gray heads who went through the various fits and starts look about at what’s going and recognize it quite clearly as “this is how things look at the beginning.”
We are really only a few years into all this stuff, and the real taking it very seriously has only been about 8 months. Web standards took 8 years to be barely usable. That was built on 30 years of internet standards that were barely usable.
That's because you're not thinking about how teams and enterprises work. You're thinking about how individuals work.
An enterprise has 20 services that each have a secret key (Datadog, Snowflake, etc). I want my team to have access to those services via coding agents. How do I guard those keys from both developer and agent? Put it behind MCP; neither dev nor agent ever sees the key. If developer leaves, revoke one OAuth cred.
I want to add access to internal and external services from one entry point without developers across hundred of teams having to sync or update their workspace. Put it behind one MCP interface.
I have enterprise skills and resources that I want to standardize and deliver to every team. But it has to vary in 10-15% of the skill body. Think same heuristics, but different specifics. MCP delivered prompts and resources can do that by dynamically templating them.
I want telemetry and data on how skills and tools are being used and I want to capture them using standard tooling like OTEL regardless of agent harness because I don't want to have to rebuild a solution on hooks if I charge vendors. MCP does that because I can capture all of the telemetry there.
> jsonschema, openapi, all of it is a better integration point than MCP.
MCP is schema + interaction model. If MCP were built on OpenAPI, it would still need another layer to describe interaction. It is effectively JSON schema + interaction flow + standard surface area.
Your argument feels like asking why do we need OAuth and OIDC when we already have usernames and passwords. They solve different problems. A simple service can just use a secret key or username + password. But more complex enterprise scenarios need the structure and flow of OAuth, SAML, and SCIM.
You’re not talking about how teams and enterprises work, you’re talking about how teams and enterprises don’t work.
Teams and enterprises had problems maintaining API keys long before there was MCP and they will have the same problems afterwards. The better teams and enterprises have had solutions for a long time.
I wish you would explain more of how you infered the handlers' KPIs here
From my point of view their purpose in life is 1) hacker news highlights or 2) to restrain some patients (me) from getting off the (Freudian) couch and mouthing off at "the folks in the waiting room"
no, there are already runoff places that will brain drain the rest. there will be no "great repatriation". it's not just "The US" and "Home", there is an ease of immigration, quality of life, and success potential gradient.
It’s completely the opposite. LLMs write awful python. Horrendous. They write pretty reasonable go and do it quite quickly.
We started in Python because of “the ecosystem”. It was a mistake. The amount of time we spend ripping out each dependency and pruning it to what we need is way higher than if we’d spent the month building out what we need. I miss compilers and LLMs will NOT generate config driven code or things that serde well. Everything has layers and layers of adapters by default and the domain model slowly erodes over time.
> It’s completely the opposite. LLMs write awful python. Horrendous.
I've been using Claude Opus and it's pretty competent. I rarely have to make steering corrections. Once I had to deal with confusion, but, overall, the code is neat and the approaches sensible. It all depends on how much context you give it to work from, for instance. If it's building on top of a well organized codebase with a good best-practices document, it performs just fine.
Right, but humans are terrible at the happy path. I’d take 20% safer on the happy path over 40% less safe in unforeseen circumstances. The failure mode being “stopped car” is also not that bad.
You’re presenting a false dichotomy. There’s the third part which is “foreseen but challenging circumstances.” Also, “stopped car” can be VERY bad in many circumstances. Stopped on lane 2 of a motorway, stopped in running water, stopped in snow.
Also I suspect many “unforeseen” circumstances happen regularly. The unforeseen part is “what” and “when.”
Hypothetical future callers, "for extensibility" abstractions, single-use helpers, ceremonial try/except blocks, and options dicts with one key all get culled.
—
But this is never the problem. Claude WILL NOT abstract and WILL NOT use your abstractions. It finds them all “ceremonial” and the idea that you could add something that might seem indirect that actually dramatically reduces the problem space is almost impossible to convey.
You can watch this in action for any API whose design you’re familiar with in a domain you understand well. If you attempt to design the same API with Claude, your will invariably get a mess of flat, insane types and no reuse. I’m talking an array of tuples of maps of set to map type insanity.
What has been helping is a mandatory pass of “Claudisms”, but even then it can only find the problem and never the solution.
reply