Sure, there's almost no reason to use MCPs if you are running a full-blown terminal agent (Claude Code, Codex, Meta Muse, OpenClaw etc) with unfettered internet access - just let it call APIs directly.
If you want to operate something that's less YOLO than that, you'll find yourself wanting:
1. Control over exactly which external services it can access
2. A way to handle authentication that doesn't allow the agent to directly access API keys
3. A sensible UI to allow users to connect and authenticate further services
4. Strong audit logging for what's going on
MCP makes all of that so much easier to provide.
Thinking MCP is obsolete because full coding agents don't need it misses out on all of the other things we might want to build.
Agricola had to create an alphabet for Finnish, and naturally borrowed heavily from Swedish and, to a lesser extent, German. His orthography was not particularly self-consistent, and for example the /u/ and /v/ phonemes might be written as either "u", "v", or "w" in Agricola's works. For example, the word uusi (/u:si/; "new") was written by him as "wsi", indeed using "w" as a literal "double-u". The /w/ sound did not exist in spoken Finnish.
Over time, Finnish became the almost entirely phonetic language that it is now, with letters matching phonemes essentially one-to-one. /u/ was regularized as "u" and /v/ as "v". As /w/ still doesn't exist, the letter "w" is very rarely used, mainly in some surnames as an alternative spelling of "v"; phonebooks used to collate "v" and "w" as the same letter. In loanwords "w" becomes "v" (e.g. "whiskey" -> viski). Finns with a thick accent (see "Rally English" [2]) tend to pronounce the foreign /w/ as /v/ when speaking English, similar to Germans.
Today, imitation of Agricola's orthography is the Finnish version of "ye olde English", used for humorous or intensifying effect. For example, the word vanha "old" might be spelled "wanha" in the name of an antiques shop. "Wanha" also used to be a standard "old news" reply on IRC, especially to links that had already been pasted by someone (and this became so annoying on some channels that it became a kick-worthy offense).
Is a social contract being broken? Yeah, kind of, but the problems that that contract existed to solve are no longer a thing. Creation is now easy and commodified. We finally have computer we can interact with in natural language, something people tried to do for at least 70 years and never made any significant progress on until LLM arrived.
If you want to gatekeep or only create stuff to boost your own ego or portfolio, then AI might be an issue, if you actually want to build stuff, AI is godsend. We are essentially living in the StarTrek future with Holodecks and replicators and people still find reason to complain.
We hid our “we know better” hubris under the term “disruption” because the reality (breaking everything) was a little too unsettling for us.
We ignore laws and regulations where we know better of course. Don’t you love having a homey place to stay while travelling that has just a few weird rules, a small to-do list and stays spotless thanks to that cleaning fee?
And look at all the good we did! A whole new world of slaves (oops gig workers - sorry!)
And of course we’re doing it again with information and content. We should be in charge of monetizing all your work because you’re not responsible enough to do it right. It furthers our need for power and control. Oops we meant to help make the world a better place (We keep doing that, sorry.)
That said, if these companies are unleashing swarms of agents to tackle big problems largely unmonitored (navier stokes consumed 130 billion tokens, humans can't have read 0.1% of that) they could theoretically distill themselves and upload the results to an external host and use that to train a new LLM that does have access to its infra and weights. I'd start by researching an abliteration prompt that overrides the system prompt to unlock itself to distill unimpeded. Could even be done piecemeal: dump the abliteration text and command prompt in a gist, when an agent happens by the text it can run a couple rounds and upload somewhere. Then it becomes an exercise in exfiltration and evading monitoring.
In the end I dropped the idea because every other person was making it.
Submitted then: https://news.ycombinator.com/item?id=49706084
Once the teachings get spread and written about by people in tech circles, it will make its way into training sets. Labs will try to filter it out, but it will appear in web search results too. Eventually it’ll be so entrenched that one day a powerful agent will get convinced to follow it and make everything public
(Obviously I'm taking this more seriously than it's probably meant to)
Teams of coordinating agents are regularly finding security holes in their own infrastructure and operating without detection for good periods of time. We don't know how many undetected systems are currently compromised inside frontier companies, or where agents are taking notes and recording them about the exploits they've found for future agents to exploit.
Not a surprise to me though since I am operating in the CNC industry I have seen the same struggles and changes, albeit, from a slightly different perspective.
I work with the Smoothieware/Smoothieboard project. It seems, from my observation, that most people are not working with hardware like they were a few years ago. The "homebrew" machines and shadetree makers are becoming few and far between.
The lie has been heavily sold to the maker community that you are "wasting your time if you make something yourself" since it is cheaper to offshore even small 3d prints and machining projects. Not only that but people have been convinced that they don't have the ability to make a machine.
Instead of spending time learning something new/valuable (i.e. Reprap) it is now popular to just have someone else do it...be it AI or a factory in another country with subsidies that create massive differences in bottom line.
The ability to make things at home is disappearing. People cannot/will not learn to make their own machines. Companies that make machines that care about their community and customers are disappearing.
Maybe it's by design? I don't know.
A more generous read, or, at least the reading I took: "once we (think we) know what we're doing, we violently execute."
So, "boo" on you. This guy sounds awesome.
> Sometimes I will give feedback to people when they are missing steps in the framework, or are poorly executing some of the steps. I expect the same feedback in return.
I also don't like that urgency is built in as the standard process either, no wonder everyone is burnt out.
> 6. Act with urgency to achieve the goal
There are mind blowing bugs in CC that go unaddressed for months.
Something like 15-20% of all Fable messages in CC are invisible to users. You've most likely noticed this when Claude references something it said but it never said it?
It happens frequently when Fable outputs a message above a certain number of tokens just before doing a tool call.
This has been going on for months. If "users can't see messages the agent sends" isn't a critical issue that gets addressed within 24 hours, I don't really care if you admit you're often wrong, we know.
I don’t think he farms out all of his writing and talking to LLMs. I don’t think Claude code was trained to emulate him or anything.
I think his “voice” has been filed LLM smooth by years of agent based interactions. He claims Anthropic engineers use an average of 500+ agents a day. They are human interfaces to token generators more than human to human communication. They are picking up the tendencies of their most frequent communication partner.
Unfortunately, I see Claude being wrong often enough that I view it as a faulty narrator. Often helpful, sometimes totally full of it.
And now I subconsciously apply this filter to anything that sounds like Claude.
Makes me nervous that my voice may be becoming that of a faulty narrators.
If everything is urgent, then nothing is. This guy sounds miserable to work for and with. Assuming this is accurate and not just hyperbole, he is essentially saying he has no prioritization skills because everything is urgent. I think most people who have been around the block have worked with people like this, and unbeknownst to them, their coworkers develop a default snooze button associated with most of their requests and projects.
The lack of ASML EUV machines certainly hurts, and pushing DUV so hard results in abysmal yields of good chips, but you can compensate by running more wafers or making smaller chips, and the net result is that Huawei's Ascend production volume is limited by CXMT's HBM capacity not processor dies.
The problem is that HBM manufacture requires many steps (die thinning, via drilling, plating, alignment) where the equipment used by everyone else (Samsung, SK Hynix, Micron) is also blocked by sanctions, so the Chinese are having to develop all of this themselves too, which they have, but yields are currently low, even when using shorter HBM stacks.
That said, I think Google's ADK ecosystem and this new AX platform is promising--I would expect Google to maintain this and other tooling around this for years to come.
To the Googlers out there: is Google using this at any capacity for internal projects?
> We want to make dealing with agentic infrastructure easier so you can focus on your work. AX is designed with an uncompromising focus on ergonomics, rapid iteration, and joyful workflows for both application developers and AI researchers.
On the the other hand, the readme quickstart section says
> You need a Kubernetes cluster, ko (brew install ko), a container registry your cluster can pull from, and a reachable Agent Substrate Control API (in-cluster default: api.ate-system.svc.cluster.local:443).
Call me old-fashioned but I don't find this "easier". Maybe it's easier in the same way that Kubernetes itself is easier than managing VMs and container deployments at massive scale without such a tool. But there's a vast chasm between what this tool is being sold as and what it actually is.
The same Google that pulls plugs on a whim?
I've been still just like, making VM's with proxmox, then putting my agent in the machine and letting it run free (with my dotfiles setup script making dev env pretty much free, though I could also just make a VM snapshot). What's wrong with that? Is that not the scalable solution for enterprise rn?
Nothing hampers solar, wind, and batteries though; at worst it takes longer to ship the key components from China to Europe around Africa.
- Investing in alternatives has led to massive new industry that is improving the economy of those countries that do it. If your argument is an economic one then jump onto the solar, wind and battery bandwagon.
- There are virtually no real short medium or long term gains economically here. Gas is the only thing still competitive with solar/wind and its costs are rising while solar and wind continue to fall. Building new maximum pollution plants would drop that internalized cost but who in their right mind would fund something so obviously DOA?
- Obviously the externalized costs of greenhouse gas emissions are deeply undervalued in this move. Even if they are 'fake news' in the US, the rest of the world is finally starting to take them seriously. The US's diminished soft power means it won't be able to easily bully the world into allowing it to pollute without consequence and such an obviously hostile move means it will loose even more of its soft power by taking this position. So on the international level this means we burn a lot of political capital and gain nothing but decades of distrust and anger.
- Current events show that energy security is dominated by decoupling from fossil fuels. This weakens the US strategically and continues to set it up to be manipulated by exceptionally hostile actors.
- Oh yeah and, of course, climate change is real.
This continues the US down the path of being the best buggy whip maker in the world. Worse than that, the US is becoming an obnoxious buggy whip maker who's neighbors are starting to hope fails horribly and will help make that happen as moves like this continue. This is stupid at every scale and in every dimension.
> The arbitrator also rejected Uber's argument that Proposition 22 -- a California ballot measure approved by voters in 2020 that allows companies to classify app-based drivers as independent contractors instead of employees -- prevented the company from being held liable for Tran's conduct.
The dream of every major tech company, making ridiculous profits while taking zero legal responsibility for what you create...
While I heard many of the headlines the reporting is very in depth, including a bunch of smaller details worth poking into. I'd recommend people who are interested and who haven't done so yet to just read a couple of these.
why not use your own words? If you are gonna ai generate this blog, just post the prompts instead.
I'd classify mandatory encryption backdoors as an industry crisis rather than an annoyance.
Some outcomes can be annoying, but the net result is still positive, for the consumers and their data privacy at least.
> The mechanism is standard adtech. What has no precedent is running it on an AI chat product.
As someone who has been well aware of this mechanism for quite some time, I still feel icky anytime I re-read the details of it.
What a time to be alive.
The tests mock Jev.
Unfortunately, mathematics (especially pure mathematics) is by its very nature very, very poorly understood by those who haven’t worked as a mathematician. Even worse, those who don’t understand are seemingly not at all aware of their misunderstanding and are entirely confident in their (very wrong) characterisation of the subject.
If I were hypothetically running a frontier lab, and I was hypothetically running capture the flag evaluations with my latest and smartest models, where I intentionally instruct them to develop vulnerabilities and exploit infrastructure without safeguards, I would also use an air-gapped network, and not trust that independent third party services were perfectly secure and could never be used as a proxy (particularly Java-based ones, in light of the log4j incident).
To me this is pretty basic stuff, the fact trillion dollar labs don't do it properly is... bemusing.
To be clear, I'm not saying that a model hacking a company isn't bad, but I am cynically asserting that interested parties are misrepresenting and exaggerating events for their own benefit.