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.
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
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.
Sorry I meant it's too dangerous to be released.
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.
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
However, I just don't think that's realistic. It's asking an author to suddenly become an editor. It's asking somebody who writes code to now read and debug others code.
It can actually be harder to find the the bug in a tricky piece of code than it can be to write your own correct code from scratch. I see AI introduce all sorts of bugs all the time in my personal projects that I would never introduce, and would never think to test for, especially around anything graphical.
1. You must be 18 to use Dropbox. Previously, you had to be 13 if in the United States, or 16 if higher. Dropbox may use information "Dropbox may use and rely on information from third parties, including age signals from app stores, for the purpose of enforcing this restriction."
2. Your account may be terminated if you don't have a Paid account and haven't accessed for 6 months. Previously, it was 12 months.
3. If you have multiple accounts tied to the same email address, and one is banned, the others may also be banned.
4. "Refunds are only issued if required by law." -> "Refunds are only issued in limited circumstances or if required by law."
5. You automatically agree to the new terms if you continue to have an account. Previously, it was only if you continued to use the service.
6. Some terms covering Teams accounts.
Pretty grim that a life critical system wasn't designed to report that the backup fibre was unserviceable until they attempted to switch over to it.
I wonder how long it was down? Days, weeks, months?
It was an amazing book.
Why would I want a bluetooth scanner to phone home? Seems untrustworthy. Nearby Glasses wins from a data safety perspective.
DXOMARK sells test equipment and consulting services for (among others) camera tuning.
Naturally, they won't attack the image quality of a customer who purchased their test equipment and/or consulting service (usually not publicly known who did that), so they often tone down some of their statements when they review a device (and shift the attention to other areas).
Always interesting to check out the scores of DXOMARK competitors in parallel, e.g. VCX[0] which strives for an objective scoring scheme (but didn't test the device yet, indicating that they at least didn't have an early sample)
Odd bokeh was one of the risks of adding a mechanical aperture, and bokeh is very often weirdest at the first or second down from open.
I would hope that the telephoto lens does not show this so severely (because it has a fixed round aperture) but all mobile phone lenses in my experience have had a tendency towards a sort of concentric-ringed, quasi-soap-bubble bokeh; it's a common part of the challenge of really tiny optics (that you either like or dislike). (The iPhone X was really distinctive in this regard). So it's not too surprising to see the aperture do this on top of that.
As a general rule you don't see it in average images, but I guess sensors are now high-enough resolution that it's becoming more obvious, and the blades of a mechanical aperture might make it quite noticeable in some situations.
Edit: e.g. the tree in one of the images in the page: https://www.dxomark.com/wp-content/uploads/2026/09/PoleHDR_D...
- there are now ridiculous vibe coded localisation in VS2026
- task manager started to not report cpu usage correctly recently (the number becomes stalled)
- file explorer display the "loading" icon infinitely on some directories
- and many other things!
The tests mock Jev.
btw its the same google that has already killed its "gemini cli" and re-introduced it in the form of "antigravity cli"
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?
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.
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.
Younger veterinarians are drowning in school debt and can't buy the practices from the older folks that are retiring. So, private equity is basically snatching all of them up right now, betting that childless millennials are going to pay tons of money on veterinary care when their pandemic pups begin to reach end-of-life.
They're going to cut wages for all the staff, and hike all the prices, because unlike with human medical care, there's hardly any regulation (yet).
The steelman argument is that private equity is just property rights. If I build a business I get to decide what to do with it.
What most people are arguing against is a specific kind of PE where an institutional investor will either use aggressive financial engineering to force a profit, even if it kills the business, or when those same investors aggregate market share to the point where it is detrimental to consumers. Sprinkle in a little bit of heartless MBA bullshit, and that is what people specifically don’t like.
They like companies with some kind of moat that makes it hard to unseat them. Basically, companies where there is no alternative for the consumer. That way, they can inflict abuse but know there will be nowhere to run.
There are two different ways to achieve this. Monopoly and regulation. Hospitals have both government granted locational monopoly and tons of regulations that make it impossible to compete.
Private equity is the symptom, not the disease.
Until we get at the disease, new monsters will be born with different name filling the same ecological niche. It's economic natural selection played out in the environment we created.
For example Krita. https://krita.org/en/download/ FOSS but you can buy it on Steam, Microsoft Store, Epic Store, and Apple Store. You get one exclusive feature, automatic updates (and more recently Steam Cloud sync support), and you also support the developers (on the other hand Valve, MS, Epic, and Apple also gets a cut too).
If you read for example the Steam reviews everyone points out that it's a free software but buying on Steam is also a good and very importantly straightforward way to support the devs + the platform itself has such a pull ("buying games you never play") that people buy it just for the case of having it in their library
The original authors of Free Software and open source were career academics and others who were paid to do other things, or were sponsored by scientific and defense research grants. I don't know how anyone got the nutty idea that you could make money on FOSS itself. Practically every time someone has tried to make money on FOSS it has failed.
(Edit: this comment previously ended with "...from Netscape on down.")
- 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.
Nothing hampers solar, wind, and batteries though; at worst it takes longer to ship the key components from China to Europe around Africa.
The ladder has collapsed. No more juniors to mentor and grow (in some cases no more US hiring period), and all of the carrots have been replaced with sticks. If you're lucky, the reward for doing good work and being nice is 'not being laid off', but the promo budget is gone and it's not like your boss gets a say in who's laid off so may the odds be ever in your favor.
Unfortunately, this is something you have to learn through experience and cannot be taught by someone else.
It goes both ways, and I would argue the spiral happens because the other side expects something above an beyond the possible.
One can indeed argue what is the best way to deal with the problem of kids and social media, but I think the article is misrepresenting the situation.
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.