> I’d like it to eventually pay for itself [...] — but that’s a problem for later.
Hard pass from me dawg. If you don't know the business model now, folks like me are tired of trusting their data to randos on the internet without a plan for sustainability. Guaranteed to end up being just another data farm.
I'm getting tired of everyone saying "MCP is dead, use CLIs!".
Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills.
The problem with tossing it out entirely is that it leaves a lot more questions for handling security.
When using skills, there's no implicit way to be able to apply policies in the sane way across many different servers.
MCP gives us a registry such that we can enforce MCP chain policies, i.e. no doing web search after viewing financials.
Doing the same with skills is not possible in a programatic and deterministic way.
There needs to be a middle ground instead of throwing out MCP entirely.
I feel like I don't fully understand mcp. I've done research on it but I definitely couldn't explain it. I get lost on the fact that to my knowledge it's a server with API endpoints that are well defined into a json schema then sent the to LLM and the LLM parses that and decides which endpoints to hit (I'm aware some llms use smart calling now so they load the tool name and description but nothing else until it's called). How exactly are you doing the process of stopping the LLM from using web search after it hits a certain endpoint in your MCP server? Or is this referring strictly to when you own the whole workflow where you can then deny websearch capabilities on the next LLM step?
Are there any good docs youve liked to learn about it, or good open source projects you used to get familiar? I would like to learn more
You need to go back to LLM tools. Before MCP, you could write tools for your LLM to use by normally using Python, something like this:
@tool def do_great_thing(arg: string) -> string:
// todo
The LLM now understands that to do the great thing, it can just call this function and get some result back that - which it will use to answer some query from the user.
Notice that the tool uses structured inputs/outputs (the types - they can also be "dictionaries", or objects in most languages - giving the LLM powerful capabilities).
Now, imagine you want to write this in any language. What do you do?
Normally, you create some sort of API for that. Something like good old RPC. Which is essentially what MCP does: it defines a JSON-RPC API for tools, but it also adds some useful stuff, like access to static resources, elicitation (ask user for input outside of the LLM's chat) and since the MCP auth spec, an unified authorization system based on OAuth. This gives you a lot of advantages over a CLI, as well as some disadvantages. Both make sense to use. For example, for web usage, you just want the LLM to call Curl! No point making that a MCP server (except perhaps if you want to authorize access to URLs?). However, if you have an API that exposes a lot of stuff (e.g. JIRA) you definitely want a MCP for that. Not only does it get only the access you want to give the LLM instead of using your own credentials directly, now you can have a company wide policy for what can be done by agents when accessing your JIRA (or whatever) system.
A big disadvantage of MCP is that all the metadata to declare the RPC API take a lot of context, but recently agents are smart about that and load that partially and lazily as required, which should fix the problem.
In summary: whatever you do, you'll end up with something like MCP once you introduce "enterprise" users and not just yolo kids giving the LLM access to their browsers with their real credentials and unfiltered access to all their passwords.
For my requirements, over 90% of the LLM integrations and rollouts have it exactly backwards. The only thing you want these agents doing is building modular, testable traditional CLI tools which can then be scripted as easily by a human or agent with almost no context/learning required. Humans must distill the probabalism of agent output into composable deterministic functions.
Pushing opaque probabalistic black boxes into the execution of your day to day operations, communications, whatever it is, is horrible even if it works. At best it’s a pyrrhic victory. I see startups using these agents to mitigate healthcare disputes.
There’s no such thing as a domain that resists modeling but for which you could accept a probabilistic result. Probabilistic must also mean probabilistically acceptable. We have words for the only counter examples: drafting, brainstorming, maybe triage.
There is not a lot to learn to understand the basics, but maybe one step that's not necessarily documented is the overall workflow and why it's arranged this way. You mentioned the LLM "using web search" and it's a related idea: LLMs don't run web searches themselves when you're using an MCP client, they ask the client to do it.
You can think of an MCP server as a process exposing some tools. It runs on your machine communicating via stdin/stdout, or on a server over HTTP. It exposes a list of tools, each tool has a name and named+typed parameters, just like a list of functions in a program. When you "add" an MCP server to Claude Code or any other client, you simply tell this client app on your machine about this list of tools and it will include this list in its requests to the LLM alongside your prompt.
When the LLM receives your prompt and decides that one of the tools listed alongside would be helpful to answer you, it doesn't return a regular response to your client but a "tool call" message saying: "call <this tool> with <these parameters>". Your client does this, and sends back the tool call result to the LLM, which will take this into account to respond to your prompt.
That's pretty much all there is to it: LLMs can't connect to your email or your GitHub account or anything else; your local apps can. MCP is just a way for LLMs to ask clients to call tools and provide the response.
1. You: {message: "hey Claude, how many PRs are open on my GitHub repo foo/bar?", tools: [... github__pr_list(org:string, repo:string) -> [PullRequest], ...] }
2. Anthropic API: {tool_use: {id: 123, name: github__pr_list, input:{org: foo, repo: bar}}}
3. You: {tool_result: {id: 123, content: [list of PRs in JSON]} }
4. Anthropic API: {message: "I see 3 PRs in your repo foo/bar"}
that's it.
If you want to go deeper the MCP website[1] is relatively accessible, although you definitely don't need to know all the details of the protocol to use MCP. If all you need is to use MCP servers and not blow up your context with a massive list of tools that are included with each prompt, I don't think you need to know much more than what I described above.
Maybe it's because of the example, but if the LLM knows the GitHub CLI and I bet it knows it, shouldn't it be able to run the commands (or type them for us) to count the open PRs on foo/bar?
However I see the potential problem of the LLM not knowing an obscure proprietary API. The traditional solution has been writing documentation, maybe on a popular platform like Postman. In that case the URL of the documentation could be enough, or an export in JSON. It usually contains examples too. I dread having to write and maintain both the documentation for humans and the MCP server for bots.
It can and it does especially combined with skills (context files). It can hit REST APIs with CURL just fine. MCP is basically just another standard.
Where it comes in handy has mostly been in distribution honestly. There's something very "open apis web era" about MCP servers where because every company rushed to publish them, you can write a lot of creative integrations a bit more easily.
Ok so in a situation like regular orchestration you would essentially layout all possible steps the LLM can take in your code in a big orchestration layer, and if it hits the sensitive endpoint the orchestration that can occur past that will block off web search. In the design that is. But for something like a manus style agent where you're outsourcing all the work but allowing it to hit your MCP it just becomes a regular API the LLM can call
It is a weird trend. I see the appeal of Skills over MCP when you are just a solo dev doing your work. MCP is incredibly useful in an organization context when you need to add controls and process. Both are useful. I feel like the anti-MCP push is coming from people who don't need to work in a large org.
> I feel like the anti-MCP push is coming from people who don't need to work in a large org.
Any kind of social push like that is always understood to be something to ignore if you understand why you need to ignore it. Do you agree that a typical solo dev caught in the MCP hype should run the other way, even if it is beneficial to your unique situation?
Isn’t it possible to proxy LLM communication and strip out unwanted MCP tool calls from conversations? I mean if you’re going to ban MCPs, you’re probably banning any CLI tooling too, right?
Nope, random MCP server where no one looks into its code is a bit more unsafe then a command you see (and can approve) executed in shell you control. In case of MCP it can do antything, and you don't see it.
Skills are just prompts, so policy doesn't apply there. MCP isn't giving you any special policy control there, it's just a capability border. You could do the same thing with a service mesh or any other capability compartmentalization technique.
The only value in MCP is that it's intended "for agents" and it has traction.
> Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills.
I have been keeping an eye on MCP context usage with Claude Code's /context command.
When I ran it a couple months ago, supabase used 13.2k tokens all the time, with the search_docs tool using 8k! So, I disabled that tool in my config.
I just ran /context now, and when not being used it uses only ~300 tokens.
I have a question. Does anyone know a good way to benchmark actual MCP context usage in Claude Code now? I just tried a few different things and none of them worked.
> I'm getting tired of everyone saying "MCP is dead, use CLIs!".
The people saying this and attacking it should first agree about the question.
Are you combining a few tools in the training set into a logical unit to make a cohesive tool-suite, say for reverse engineering or network-debugging? Low stakes for errors, not much on-going development? Great, you just need a thin layer of intelligence on top of stack-overflow and blog-posts, and CLI will probably do it.
Are you trying to weld together basically an AI front-end for an existing internal library or service? Is it something complex enough that you need to scale out and have modular access to? Is it already something you need to deploy/develop/test independently? Oops, there's nothing quite like that in the training set, and you probably want some guarantees. You need a schema, obviously. You can sort of jam that into prompts and prayers, hope for the best with skills, skip validation and risk annotations being ignored, trust that future opaque model-change will be backwards compatible with how skills are even selected/dispatched. Or.. you can use MCP.
Advocating really hard for one or the other in general is just kind of naive.
IMO if you want a metadata registry of how actions work so you can make complicated, fragile, ACL rule systems of actions, then make that. That doesn't need to be loaded into a context window to make that work and can be expanded to general API usage, tool usage, cli usage, and so on. You can load a gh cli metadata description system and so on.
MCPs are clunky, difficult to work with and token inefficient and security orgs often have bad incentive design to mostly ignore what the business and devs need to actually do their job, leading to "endpoint management" systems that eat half the system resources and a lot of fig leaf security theatre to systematically disable whatever those systems are doing so people can do their job in an IT equivalent that feels like the TSA.
Thank god we moving away from giving security orgs these fragile tools to attach ball and chains to everyone.
> MCP gives us a registry such that we can enforce MCP chain policies
Do you have some more info on it?
looking up "registry" in the mcp spec will just describe a centrally hosted, npm-like package registry[^1]
[^1]: The MCP Registry is the official centralized metadata repository for publicly accessible MCP servers, backed by major trusted contributors to the MCP ecosystem such as Anthropic, GitHub, PulseMCP, and Microsoft.
I agree, and it's context-dependent when to use what (the author mentions use cases for other solutions). I'm glad there are multiple solutions to choose from.
Schema validates structure, nothing validates intent. That's the actual attack surface and nobody's talking about it.
CLI `--help` is baked into the binary. You'd need a new release to change it. MCP server descriptions can change between sessions and nothing catches it.
Honestly though, the whole thread is arguing about the wrong layer. I've been doing API infra for 20 years and the pattern is always the same: if your API has good resource modeling and consistent naming, agents will figure it out through CLI, MCP, whatever. If it doesn't, MCP schemas won't save you.
Thanks for the CVE reference, hadn't seen that one.
> FYI man, alright. You could sit at home, and do like absolutely nothing, and your name goes through like 17 computers a day. 1984? Yeah right, man. That's a typo. Orwell is here now. He's livin' large. We have no names, man. No names. We are nameless!
Cereal leaves the room. He’s gone for like 15 seconds. Mom pops her head in:
“Help yourself to anything in the fridge. Cereal has.”
That always cracks me up. Like he had to have walked out of the room, spun on his heel, and marched straight into the kitchen and raided the fridge. He couldn’t have taken more than 5 breaths after leaving before he was eating something.
Purposefully devaluing the dollar to make US goods more globally marketable and hide the Japanese debt crisis is an interesting but risky strategy.
Currently, I'm glad to see a correction without panic, but it's too early to make a call on the effect on the overall global economy. Xi's already suggested making the Yuan a global reserve currency, and seeing as much debt they're holding, I'm a little worried they're able to make it happen if this is the US financial strategy.
The channel appears to be five years of "It is happening!" and "It started!" thumbnails. I just can't take it seriously, so I decided to look into the company/leadership.
It appears they've been associated with a lot of hype/fear copy-paste companies that offer highly inflated monthly access to their trades and research. Note that they were named "Game of Trades" before rebranding.
> It appears they've been associated with a lot of hype/fear copy-paste companies that offer highly inflated monthly access to their trades and research. Note that they were named "Game of Trades" before rebranding.
I really wish that people would wake up to the danger posed by meme stock BS “leaking” into the general markets.
Just as voters are responsible for changes in society, uninformed investors can impact society too, especially when they’re amplifying their purchasing power via leverage.
For instance, I’ve been buying real estate forever, and I’ve enjoyed the Reventure app.
But I’ve REALLY noticed that his YT videos are exclusively doom and gloom.
This ceaseless negativity moves markets, just as the irrational exuberance for real estate in 2005 moved markets.
But the exuberance for real estate was driven by people who were buying real estate.
The endless doom and gloom of YT finance videos is for a much different reason:
It drives page views.
That’s not a good thing. Because it’s really easy to get swept up in the negativity. And that negativity has a downstream effect, where it’s often used to convince people to invest in things that the YouTuber is promoting.
Basically, I don’t know if we need an “SEC for YouTube,” but we might.
Yes, I know we already have an SEC for YouTube (it’s the SEC), but nearly none of the people doling out financial advice on YT are trained professionals. It’s the fundamental defect of internet advice; who to trust?
Misinformation and mass hysteria suck, I agree. But if the amplification of the sky-is-falling-flavor-of-the-week braindead youtuber take can materially imperil financial markets, the stability of that system was always doomed.
An “SEC for YouTube” can’t prevent shit if the lever of influence is already that long. It might be able to keep a lot of meme investor idiots from losing their shirts, but that has to be weighed against the historically evident risks of having what amounts to a ministry of truth/state propaganda regulator.
I remember sky-is-falling-flavor-of-the-week newsletters from the 1970s; they probably go back further than that, but I don't remember firsthand. The difference is that YouTube lets millions of people find this without either having to subscribe to the newsletter, or the newsletter having to figure out who they are and send them a free copy.
In other words, what's different is that the gain is higher. The system was not always doomed, because the gain wasn't this high. Now that it is this high, the system may now be doomed.
He was on at one in the morning, and a big chunk of his audience was calling in to the show drunk or high. 99% of the audience knew it was fake.
And twenty years later, the conspiracy stories live on, via YouTube, but without the CONTEXT that the Art Bell show was broadcasting to a VERY niche audience.
The channel appears to be five years of "It is happening!" and "It started!" thumbnails. I just can't take it seriously, so I decided to look into the company/leadership.
Reminds me of ZeroHedge. They've been shouting that the depresssion-level market crash is near now since 2009. Every single day. For 17 years.
i don't think that's a fair representation of the average of the ZH articles.
many bird's eye view articles are depicting how the game is rigged and corrupt to the core and that it is heading towards a wall (and you should buy x, typically gold)... yes.
but then they also have more day-to-day articles discussing market moves and predictions in all directions.
ZH is a wider range of stuff than that. and in all that noise, most of the important alternative, often initially censored news appeared there first.
so, yeah, don't take it all in literally... but then it's a site edited by Tyler Durden FFS... :)
I can only personally speak for myself and I'm not giving financial advice here. I use the Bolgehead strategy of the 3 fund portfolio is still the tried and true I follow, and I have yet to not benefit from doing so, even in economic downturns[0]
I'm immediately concerned with the note about silver dropping so much. Yes, that happened, and was a historic drop. But it followed a historic run up to its prior price, so the drop is still net positive for even a 1 month period.
I'm not saying the article's thesis is incorrect, but its providing some data without context. I'm always leery of data presented without context.
I take “not financial advice” articles like this at best as entertainment. How can anyone seriously talk about metals for example without mentioning that gold was $1900 and silver $20 a few years ago. Today they sit at $5000 and $80. It’s completely absurd to write about the “drop” as a proof of anything
this article discusses the events in the recent couple of months, explicitly. the moves prior to that is not really relevant for its thesis -- regardless of how true it actually is.
The bar has been significantly lowered in the last year since the US has decided to commit bigly to unpredictability. Another 3 years of these kinds of manipulations and the Yuan could very well look like the lesser evil to a lot of countries.
I don't understand why gold-backing is required. I'm a novice.
My understanding is that a reserve currency requires fluid markets and a stable, reliable, metrics-based currency policy. It's why the Fed is so stubborn about its relatively simple policy goals: 2% inflation and low unemployment.
China appears to be attempting to reproduce what the USD was before it was free floating.
USD is currently backed by debt and nominally military might. If the US defaults then all of the US bonds held by foreign banks become worthless. That is an enormous risk which is why countries have been divesting from US bonds. If USD was still gold, as it was before 1913, if you hold your money it cannot be made worthless by a third party. After 1913 USD became gold backed bills with partial reserve. It is why USD became the global reserve currency. But, reserve requirements were reduced and more paper was produced. In 1971 Nixon removed the convertibility of paper bills to gold metal effectively stealing the gold of any nation that asked the US to hold it.
One of my favorite bits of currency trivia is that a $20 double gold eagle coin used in circulation prior to 1933 had a gold content of 0.9675 troy ounces. Twenty dollars in your hand was literally nearly an ounce of gold.
This simplistic explanation seems to elide the very point it makes ... a gold backed currency becoming a non-gold backed currency was done via a political decision making process, just as any decision to default on US national debt would be.
You seem to suggest that people should worry about a default claiming if we had still had a gold backed currency the risk would go away ... "if you hold your money it cannot be made worthless by a third party" ... but it can be made worthless by a government any time that government chooses.
The government (having defaulted on gold-backed debt) could simply refuse to convert the paper of the debt to gold (sure, that would be bad, but hey, they've already chosen to default, so not much worse ...)
Oh no! You have found the fatal flaw of using paper currency backed by anything. Before 1913 money was gold and silver. Not paper bills backed by those metals.
Many people doubt that returning to gold and silver coinage is possible. Going to gold backed currency is a step in the right direction.
A full reserve requirement might work for paper currency. But the only way the plebs that are stuck with paper can truly secure their wealth is to use metal the same as countries do.
1. old situation: currency backed by full (gold) reserve
2. actual political decision: currency no longer backed by full reserve
3. result: currency no longer backed by full reserve
1. possible political decision: return to currency backed by full (gold) reserve
2. possible political decision: currency no longer backed by full reserve
3. result: currency no longer backed by full reserve
To whatever extent government could return a full-reserve backed currency, government can move away from that again. Thus, there's no builtin security for anyone in a return to a full reserve backed currency.
If no government in the history of the world had ever done this, then arguing for a full-reserve backed currency might have a bit more weight. But they have, and it really has done.
Your first point is wrong. Before 1913 gold and silver coins were the money in peoples pockets. Government produced the coins of known weight and purity. After 1913 paper bills were produced with partial reserve. The US has never had a full reserve paper currency. Step one of going to gold backed paper always comes with printing more paper than there is gold. Wanting to spend more money than they have is the reason every time a government debases its money.
Regardless, I get your point that political decisions ruined it. It is clear that government cannot be trusted to maintain a constant unit of measure that money should be. So, would you agree to an amendment to separate economy and state? Require government to produce coins of known weight and purity and that is it. If they want more money to spend they will have to extract it as taxes.
> Pretty straightforward really. You combine Brazil's history of monetary stability, with Russia's respect for property rights, India's domestic tranquility, China's financial transparency, and South Africa's investment opportunities - and hey presto, you've got a new global money
Of course more countries may enrol in the system, but that dilutes the influence of the five namesake nations of BRICS.
But then you have to choose an actual currency(s) to do transactions in, so will you trust them to be stable? Or perhaps go with a 'theoretical' currency likes Keynes' bancor?
All reasons that a paper currency backed by gold has never lasted long. Going to paper currency is the first step to start cheating by fudging numbers. The only money that has ever lasted is actual coins/bars of metal, precious or otherwise.
> The only money that has ever lasted is actual coins/bars of metal, precious or otherwise.
1. most physical paper has a relatively short life, so one would not expect it to last as long as metal tokens
2. paper was only available in much of the world several thousand years after the first currencies began, so it's not suprising that we have little record of paper money from very old civilizations.
3. the idea that there was no cheating by fudging numbers before paper currency is completely ahistorical. The nature and ease of the fudging may have changed, but the fudging itself existed long, long before paper currencies became common.
The entire reason coinage was even a thing was exactly this! Turns out it's pretty hard to know if a coin is actually the amount of gold it represents, if the shopkeepers scales are accurate etc etc. etc
The entire concept of marking coins with trustworthy seals was exactly to basically invent fiat currency as risk mitigation: coins bearing the seal would be honored, and from that it was a short hop to "what if I just presented an IOU with the seal of the local gold merchant?"
DO NOT make financial decisions based on the advice of a youtube channel.
DO NOT make financial decisions based of of the advice of an an article written by a know associate of Curtis Yarvin.
You saw the video yesterday because this is a marketing exercise.
They hold a stake in the outcome, you are the greater fool.
Christ.
Find a professional fiduciary that doesn't have a youtube channel and never speculate more than you can afford to lose.
> Curtis Guy Yarvin (born 1973), also known by the pen name Mencius Moldbug, is an American far-right political blogger and software developer. He is known, along with accelerationist philosopher Nick Land, for founding the anti-egalitarian and anti-democratic philosophical movement known as the Dark Enlightenment or neo-reactionary movement (NRx).
If one of those meanings is "one who hides their support for fascism", it doesn't apply, as they've made public displays of support. It's just that most people know them for their technical accomplishments without doing further research on who they are. This is understandable, hence my warning.
Everyone in the IDW or who followed Mencius moldbug always told normies they weren’t fascist and that you just called them Nazis because you disagreed with them until the current day when they are now more open about being in what they consider a post Constitutional era.
That’s why they were called cryptofascists even though I agree they’ve dropped the hidden part since they feel they have the power to get away with it.
This really should be pinned to the top of the thread. Finance-as-entertainment is the world's worst gatcha game. For some reason people love getting suckered by these far right idols, both financially and "intellectually", who in turn are playing three-card-monte with them.
Everyone forgetting the more likely, more rule-of-law based fallback option for a reserve currency and international payments system (which is the important bit!): the Euro. Digital or otherwise.
> Xi's already suggested making the Yuan a global reserve currency, and seeing as much debt they're holding, I'm a little worried they're able to make it happen if this is the US financial strategy.
I wonder why you’re worried. Regime’s change all the time. From a third party perspective, China is no better or worse than the US. Also, given how literally every country under the sun despises US now, this might just happen.
The way China manages it's currency is very different to how the US manages theirs.
China maintains strict controls on capital flows in/out. A reserve currency requires free convertibility. Holders need to move large sums instantly without permission. China has repeatedly tightened these controls during stress periods (2015-16 devaluation fears, for example).
Limited access to Chinese bond markets and equities for foreign institutions. Reserve currency status requires deep, liquid markets where central banks can park hundreds of billions. US Treasury market is $26T and extremely liquid. Chinese government bond market is smaller and less accessible.
Reserve currency issuer must run persistent current account deficits to supply the world with currency. China's economic model is built on export surpluses. They'd need to fundamentally restructure their economy.
This is PRC's fundamental disagreement. US reserve currency morphed into high liquid, high speculative instrument to fund unsustainable debt, hollowed out domestic industry (triffin)... but this is not by design. It's the result of emergency adaptations moving off gold, then people post rationalize the trinity musts (open capital, floating rates, independent central bank) is what makes reserve when it's unintended structural outcome from failed gold peg.
Now we see hints of end stage USD reserve behavior, debt snow balls and reserve controller will pull the our dollar, your problem card. This US doing current conniptions trying to either reduce USD strength or inflate away debt... costly instability. People forget, liquidity / storage only matters to sovereign buyers who needs reserve for utility... everyone else (now plurality) are private buyers who buy for returns. If we enter end of dollar cycle and USD reserve cost them money, then they go elsewhere
Elsewhere is what PRC wants to offer, HIGHLY CONTROLLED, BUT STABLE reserve pegged to PRC industrial chains, i.e. real economy instead of speculative financialization. This what recent yuan reserve talk is from (note it was old Xi speech republished in Qiushi), so the propose model isn't even in response to current USD conniptions but prediction on end life of US behavior when USD reserve goes from exorbitant privilege to just exorbitant.
It's precisely because logical outcome of current reserve "musts", i.e. triffin charity/global good that makes it ultimately a stupid arrangement where the system breaks when US/owner can't afford to maintain or develops bad habits (deficit spending). Hence, what PRC plans to offer in parallel: stable regulated reserves for "real economy" financial utility. Stable Yuan "bank" reserve can coexist with volatile USD "casino" reserve. Now of course this all heterodox theory, but we are seeing theory of USD reserve limits peaking it's head, and PRC not retarded enough to pickup triffin baton. IMO PRC fine with US dealing with triffin headache and IMO betting US will fuck global creditors when shit hits fan, i.e. they waiting for USD reserve to implode due to inherent contradictions, to show world precisely why yuan reserve not modelled to repeat same mistake.
1. No one sane trusts EU after RU sanctions either.
2. Euro share of SWIFT shrunk from ~40% to ~20% post URK war. Part of this technical (t2 reforms), i.e. actual reduction not as dramatic, but Euro as toxic as USD with even less leverage.
Meanwhile PRC went from single digit % cross border settlements 10 years ago to 50%+, plenty of the world trust PRC with their money, not just money but PRC alternative to SWIFT financial plumbing, CIPS. Meanwhile PRC also recycling it's surplus USD to lending... i.e. they're financing more than imf/worldbank/paris club right now. Another indicator that countries "trusts" PRC to manage monetary system, or rather they balancing from losing trust of west.
TBH trust is western mindless muh reserve orthodoxy nonesense. Ultimately PRC has much stronger reserve posture for the same reason US did... for 80+ years countries needed USD for US techstack and then petrodollar, aka modernity was locked behind USD, all the other muh reserve "needs" is downstream of that. Need > trust.
Ironically where trust actually comes in is whether PRC TRUSTS others. Qiushi suggests PRC stable reserve functions something like panda bond lending, where PRC lends liquidity to trusted VIP (real economy) players. Everyone else can keep gambling with USD reserve with high likelihood of debasement. It looks like PRC doesn't want be THE reserve, they want to be VIP reserve while THE (USD) reserve burns.
> 1. No one sane trusts EU after RU sanctions either.
The RU sanctions were implemented 'only' because RU invaded another country. If you don't plan on invading countries is there much to worry about?
To a certain extent if you 'just' want to participate in the world economy the EUR seems fine. If you're looking to start geopolitical drama with military actions, is there any currency of a major economy that would not be a risk? Major powers tend to want stability, which would allow them to stay major, so would frown upon anyone stirring the pot (besides, perhaps, another major power: see China with Russia against UA/EU).
Europe wasn't breaking sovereign immunity / sovereign bank seizures when historically fighting each other, current actions historically unprecedented. So the answer is war is not sufficient excuse for RoW. EU extra delulu because RU/UKR not even over direct EU/NATO territory i.e. EU breaking sovereign immunity over "peripheral" interests. Like EU seize/sanction US when? Point of sovereign immunity is provide some semblance of neutrality for rest of world to do their thing while drunks fight, neutrals still want to buy from the drunks, EU has made things both hard not neutral.
Settlement and reserve currencies are two very different things. The USD isn't great as a reserve currency but it is still better than all the other options.
Settlement is leading indicator / proxy of trust. The point is countries trust in PRC running financial pipes is increasing, because vs US/EU, PRC simply look more responsible.
USD treasury isn't great now AND trending towards bag holding catastrophic "our dollar your problem" depending on debasement velocity. Hence central banks ditching dollar for gold etc... it's still currently better than other options in the sense that no other options really exist except metals with no counter party risk. More this happens the more exorbitant and less privilege USD becomes, the worse it serves as reserve, the more opening for alternatives. This where PRC eventually comes in, i.e. recent reserve talk is for eventuality not hand off. In the meantime they are banking on USD being not great, and getting worse. Which increases rates -> increase debt finance / servicing cost. The system is getting worse for everyone, including US. Don't underestimate watching US debt servicing growing from 1T to 2T in a few years when US realizes exorbitant reserve currency without privilege is not worth maintaining. Waiting for US to recognize USD reserve isn't great for US is part of the transition.
The sequence of events: Elon doing a leveraged buyout of X, then xAI funding, then debt transfers to X, then the xAI–X stock deal. Now the proposed SpaceX–xAI merger appears to have shifted X’s financial burden from Musk personally toward xAI investors and, potentially, future SpaceX shareholders.
This is speculative, of course, but yeah seems likely.
RunReveal (https://runreveal.com) | Systems Software Engineer | Austin, SF (US Work Auth required) | Full-time
RunReveal is the Security Data Platform that's building tools to help companies detect and respond to threats in their network. We're a team that values speed, quality and curiosity. Our stack is Go, NextJS (TS), Postgres and ClickHouse. We believe that companies should be able to own their security data and get value out of it too and so we've built a platform that can be deployed anywhere. SIEM sucks, so we're here to fix it.
If you're into self hosting or running a homelab, or you're using LLMs to enhance your development workflow and extend your knowledge and not just regurgitate slop, or you're always looking for opportunities for self improvement, you're in good company at RunReveal.
We've got phenomenal customers like Cursor, Harvey, Temporal, Linear, DigitalOcean, ClickHouse and AngelList among many others that we work with on a daily basis to improve the product.
We're especially interested in folks that have experience working with petabyte scale databases. We use ClickHouse, but experience with other similar large scale data technologies like Iceberg, Flink, Spark, ScyllaDB, Cassandra, InfluxDB, TimescaleDB, BadgerDB etc would also be valuable.
Reach out to me via alan at the company domain and mention hn who's hiring January '26 in the subject line.
> it prevents entire classes of bugs where IDs get mixed up across services.
~Does this really happen for people? I haven't ever seen this class of bug, and shudder to think of how it happens in code. Sure support tickets are nicer with the prefix, but how would a bug manifest in the code itself?~
Edit: of course it can happen with `new.id = old.id` where new and old are different types, now that I think about it after coffee. However, I'd be hesitant to claim that this prevents those bugs, instead I'd argue that it simply makes them easier to identify.
Also, KSUID has been around since before UUIDv7 and seems to meet all of the author's same requirements and has many client libraries already. Guess people doing research on it still aren't able to find it, or just want to do their own anyway which is cool too.
A few things here, one is that getting them mixed up isn't the same as them ending up in the wrong place. Looking fruitlessly for a missing user with id 9287dfn9384f that has some support ticket only to find out later that this was their order ID and the wrong thing was put in a form (particularly if you ask users for something, I see 4 different IDs floating around, which is my customer/user/product/order/shipping id?). If the user id is "order_1239123" I know to go and look at the orders table, not "dance around all tables trying to find what on earth the id could relate to".
However there are two other ways this happens which come to mind:
1. HTTP API calls. There's a whole untyped layer going on here. You could have a PUT to set some content, and create a new entry if one doesn't exist - there's a place for a call to go to the wrong place but succeed. If two entities have the same structure but are different things this can be harder to spot.
2. Manual entry. This is the bigger one. Vast amounts of workflows have somewhere that a human does a thing, and that will go wrong at times. An excel file uploaded to the wrong place, the wrong header, the wrong bit typed on a form.
A counting up of numbers is a simple ID but awful for both of these, because now you have overlapping IDs across systems. Having larger random IDs takes you out of this risky area because at some point the chance of a collision is so low as to be not worth considering, however even small IDs with a prefix like "customer_001" and "order_001" quickly removes a source of problems.
I'm not saying any of this is the only solution, or that there aren't better ones, but I can see places where this kind of thing can easily happen in the real world and "prefix the ids with a type" is a very small and simple change that can help.
I would also note that this then becomes a front facing thing that ties you into something as well though, and not all types are as nice to make public.
Maybe it's malware, I haven't checked, but that seems like a pretty typical trajectory to me. I posted a project on HN and got a graph of roughly the same shape (though a much more modest magnitude). https://www.star-history.com/#maxbondabe/attempt&type=date&l...
Star counts go vertical when you launch your project and it's warmly received. ~850 stars in 11 days for an AI project doesn't seem at all crazy to me.
The README also contains a mild inducement to star the repo.
> Star Us on GitHub and Get Exclusive Day 1 Badge for Your Networks
Seems sufficient to explain any inauthentic behavior. Growth hacking tactics are certainly not typical of open source projects, but how that should factor into your judgment of this project's trustworthiness, I can't say. Caveat emptor.
Hey, I still remember October 9th so well — that was the day we first went public with our project! I was so excited telling all my friends about it on social media. We'd been working towards this for months, getting everything ready.
Hard pass from me dawg. If you don't know the business model now, folks like me are tired of trusting their data to randos on the internet without a plan for sustainability. Guaranteed to end up being just another data farm.
Neat you got the domain tho.
reply