you dont have to go look at the Google Graveyard [0] to understand that you might try a google product one day or month to have it either disappear or become a different product incompatible with the first the next month. They have been known for this for at least decades now.
Gemini CLI was fun for five minutes of testing until it tried to rewrite my whole code base.
yeah when I read these RCE reports about public-facing software that I know about I usually upgrade them within minutes of reading the report that's why I read these reports and you really have to take them seriously because otherwise your machine gets compromised, sooner rather than later... it seems like lately there's been no advance notice on a lot of these RCE exploits that are publicly released, I mean come on guys at least give us a few minutes to upgrade our software before releasing the exploit, it feels like the late 1980s early 1990s when there was no guardrails on disclosure, i.e. all the remotely exploitable sendmail bugs. people who fail to read these reports or read them too late wind up having millions of machines being compromised because of it. currently nginx has about a 39% - 43% share of the public facing web server market today, so its pretty serious.
it could also be common sense.. you live in a noisy city and you are wondering what the noise is.... maybe it could be the city itself? how about sleep in a different smaller town and then ask yourself the same question, you'll probably get a different answer.
Facebook the web site reminds me of a really bad implementation of MySpace. MySpace was better, even in 2003. There are hundreds of usability bugs that exist on various parts of the platform that for over a decade remain unfixed. For a company that has 78,000 employees, you would think one of them might want to dig in and fix the web interface bugs. What's weird is in the age of Claude Code, it would probably take one software engineer a week to fix all of them, so its really pure incompetence. I think they spend more time on automation around restricting the usage of the platform that they forgot about the user interface bugs that plague it.
Also, avoid using Meta Pay aka Facebook Payments, where a user can send a payment to another user via the Messenger app. Someone sent me money a few weeks ago, and a two weeks alter they still have the payment marked as "Completed" on the sending side, and "Cancelled" on the receiving side. I told the sender to just do a chargeback with their bank because Facebook basically stole the money. Don't use Meta Pay for sending payments to anyone. Then when you try to open a "case" about it, you call a call center in Indonesia and the people have no access to see anything about the transaction, they just send it up the chain, only to have an automated response telling you to do something that the web site doesn't even offer as an option. I don't think there is any humans in the loop, besides the Indonesian call center that has no access to any of what you're calling about.
in 2002 I worked at an AT&T major datacenter and watched the NSA install all the black boxes in every rack, complete with a black curtain and armed guards while they did the project (St Louis). Before that it was still going on, it just wasnt so embedded like they did in 2002.
the authors reference to LLM's as "bullshit machines" is more true the less parameters you have trained in your model....as we scale up to trillions of parameters, add Mixture of Experts (MoE) architecture, this no longer is an accurate statement. Proof in point was yesterdays announcemnt of Mythos 5 model (10T parameters + MoE [1]) by anthropic where it seems to be so good at finding/exploiting vulnerabilities in source code that have been there for decades and only recently uncovered needs to be used to fix these critical vilnerabilities first before it gets released to the public, they even have a project called Glasswing [2] dedicated to letting people fix the thousands of vulnerabilities already found by the model before they release this model to the public, because it's so good at what it does... I think we're a little bit past the point of calling these models "bullshit machines" at this point...
So, you're implying that there is a second person named Alan Cox from Swansea, Wales who worked on FreeBSD, not Linux? Where is your source for that? lol
"His involvement with Linux began in the early 1990s when he was working on a project that required a stable networking solution. This led him to discover Linux, which was still in its infancy at the time.
Contributions to Linux Kernel
Cox's contributions to the Linux kernel are extensive and far-reaching. He is best known for his work on the Linux networking stack, which was critical in making Linux a viable option for server environments. Cox identified and addressed numerous issues in the kernel's TCP/IP implementation, enhancing its performance and reliability." [0]
"For those not familiar with the Linux kernel contributors, Alan Cox wrote large parts of the networking stack, was the maintainer of the 2.2 branch, and was commonly considered the "second in command" to Linus Torvalds at one point: http://en.wikipedia.org/wiki/Alan_Cox"
[1]
"Alan started working on Version 0. There were bugs and problems he could correct. He put Linux on a machine in the Swansea University computer network, which revealed many problems in networking which he sorted out; later he rewrote the networking software. [2]
The search filters and the user interface in general on YouTube is garbage. you guys need to go back to the drawing board. it really is almost impossible to find a video, you have to sort through hundreds of AI slop clickbait videos in order to get to the one that you're actually interested in finding.
whether people want to admit it or not, agent encoding is kind of the norm right now and I think the fear is the stories coming out of places like Block, Inc where they announced they fired 4,000 engineers a couple days ago because of what's the obvious truth today versus 6 months ago.... one expert software engineer can do the work of 20-40 people, so why do we need so many people? it's a hard pill to swallow, it's easier to claim that agentic coding doesn't work or that the code is sloppy and it doesn't work when in reality most companies are currently using it everyday, especially the large ones.
I agree with you, if you're already a competent engineer, your productivity only is improved by orders of magnitude by using coding agents that are at this point producing very good code as long as you give it the right prompts and you test your code and remove any bugs... if the code tests and all the bugs are removed, what you've got is a working product that is hard to argue that it doesn't work especially if there's been a lot of QA done on it and there's no bugs....
you could probably get away with just running nginx with certbot on the front end of that domain name and then have it proxy back to a script that talks to the brother printer on the back end of it to do printing, although I'm not sure why you'd want to print via the public internet
i wonder how much that costs per hour to run any normal load? what benefit does this have versuss using mysql (or any similar rdbms) for the queries? mysql/pgsql/etc is free remember, so using S3 obviously charges by the request, or am i wrong?
forcing the OS to authenticate the age of the person using the machine? age verification can easily be done by using the DMV as a conduit or using login.gov as a conduit or using id.me as a conduit. these interfaces are already used by dozens of government agencies to authenticate citizens of the United States, and there doesn't need to be any special software installed on the machine
i dont know, i'm in my 50's, and been doing software engineering work every day professionally since i was 15, and i can say claude code (max) has made me at least 20x more productive... Its definitely an improvement. I think what they've got is top notch, doesnt come close to what the competition are offering, at this point.
I tried to use Google's Gemini CLI from the command line on linux and I think it let me type in two sentences and then it told me that I was out of credits... and then I started reading comments that it would overwrite files destructively [0] or worse just try to rewrite an entire existing codebase [1]. it just doesn't sound ready for prime time. I think they wanted to push something out to compete with Claude code but it's just really really bad.
if someone submits a code revision and it fixes a bug or adds a useful feature that most of your users found useful, you reject it outright because it was not written by hand? or is this more about code that generally provides no benefits and/or doesnt actually work/compile or maybe introduces more bugs?
The way that it would make sense for age verification is if there was some federal system that verifies your identity and then it would use a public key crypto system to allow a third party to check whether or not this person is over the age or not.... common systems I see being used right now that could be integrated for this purpose would be login.gov or id.me... they could allow a token-based authentication system for verification of age without having to divulge any other information about the person. these systems are already being used by the IRS, VA, SSA and other Federal systems.
Google has zero customer service. using them for anything serious makes no business sense. the only thing that they're good for is serving ads to people, and they have a support team for that, but only if you're spending a lot of money, and even then good luck finding it
yeah exactly have you ever tried to call Google support? it doesn't exist. the only way to contact Google is by posting something on news.ycombinator.com and then hoping that some person who works at that company actually responds to you and logs in somewhere and then changes your access.
this is the long-standing problem with using Google services. either they become deprecated and removed without notification, or they outright ban you for using tools as intended. either way, using Google tools for anything doesn't make business sense to anybody who's seen the history of this.
the government should not be using any private LLM, they should build their own internal systems using publicly available LLM's, which change frequently anyway. I don't see why they would put their trust in a third party like that. This back and forth about "ethics" is a bunch of nonsense, and can be solved simply by going for a custom solution which would probably be orders of magnitude cheaper in the long run. The most expensive part is the GPU's used for inference, which can be produced in silicon [1].
to avoid these conditions i have usually inserted a row into a lock table used for this purpose to create a lock with a unique key for that row with a few minute timer, the once the transaction is complete it will delete the lock row. This way, simultaneous users will only get the first lock, all other requests would fail, and then if the timer expired, we would assume the transaction never completed and it could try again after a few minutes