Komunitas
sh.itjust.works
This blog post comes to me at an interesting time, for I’ve been gathering info to rebuild my router using FreeBSD. Specifically, I bought a hard-copy of The Book Of PF, 4th Edition, for configuring PF for routing and firewalling. Like with all good firewalls, the PF rulesets start with blocking all traffic. But unlike the VyOS-based rules used by my outgoing Ubiquiti router, PF does not implicitly include rules for common use-cases, such as enabling hairpin NAT for Legacy IP. Nor does the syntax assume that rules are only for inbound, as the shortest syntax will actually apply a rule in both directions on every interface. To that end, one of the tenants for configuring a PF firewall is to also filter outbound traffic, as a matter of: 1) asserting control over the network, and 2) implementing the principle of least privilege. I can reasonably accept that my home’s guest WiFi network should be fairly free flowing for outbound traffic, but that shouldn’t apply to my IoT VLAN. Quite frankly, my IoT VLAN only allows outbound connections to four specific NTP servers hosted by ntp.org, because my thermostat has a badly-designed real-time clock and I refuse to allow network access for devices that historically never needed it. Before containers, firewalls implemented the DMZ idea, where any host that runs an externally-accessible service would be within the DMZ, to prevent infiltrating the broader LAN if something goes wrong. Your solution achieves a sort-of DMZ, but does it at the Docker host. Whereas a true DMZ would segment the rest of your network off, so as to further reduce risk, since iptables is the only line of defense. That said, zooming out, this caught my attention: The breaking point came when I wanted to host Gemini FastAPI, a project that wraps Google’s internal Gemini API into an OpenAI-compatible interface, useful for using your Gemini Pro subscription outside Google’s walled garden. The catch: it needs your browser cookies, which means full access to your Google account. The very premise of Gemini FastAPI seems flawed to me, if it’s trying to create a wrapper when Google clearly does not want that to exist. The challenges that you observed, such as the brittleness of IP allowlists, would suggest to me that the overall endeavor is going to be brittle, by Google’s design. To be clear, that doesn’t mean you shouldn’t pursue this, in the same way that yt-dlp exists for the legitimate use for accessing YouTube. But what both yt-dlp and Gemini FastAPI will never escape is that they only exist because Google hasn’t cracked down on it further. When every indication is showing that this is the road with even more trouble beyond the next curve, is this what you want to invest time and effort into? There are other platforms and protocols that replace YouTube, or at least minimize one’s dependency on a clearly antagonistic host. At bottom, I think the question is whether connecting to Gemini is really worth all of this trouble, when they evidently don’t want you to do this, and it adds yet another dependency upon Google. Even if you believe Google is 100% benevolent and their lack of a built-in support for using Gemini externally is just a minor oversight, you will have to pick which services you will base your own infrastructure upon. This is, after all, c/selfhosted.
Komunitas
lemmy.ca
sorry for Gemini link to prompt below, but google itself doesn’t provide any top page links to answering the question, or questions about “software wifi to radio conversion”. GrapheneOS does not provide the functionality. Seems like only process to transmit/receive at a different band is to use hardware that bridges from wifi signal to radio signal. modify phone wifi frequency to arbitrary frequency It is generally not possible to directly modify the WiFi frequency on a smartphone to an arbitrary frequency. Smartphones are designed to operate within the standard WiFi frequency bands (2.4 GHz and 5 GHz) and their corresponding channels. While you can influence which band your phone connects to (e.g., prioritizing 5 GHz for faster speeds), you can’t arbitrarily set the frequency. Why you can’t set an arbitrary frequency: Hardware limitations: Smartphones are built with hardware that supports specific frequency ranges (2.4 GHz and 5 GHz in most cases). Protocol compliance: WiFi communication relies on specific protocols (like 802.11 a/b/g/n/ac/ax) that are tied to these standard frequency bands. Router configuration: While you can configure your router to broadcast different SSIDs for each band (e.g., “MyWiFi_2.4GHz” and “MyWiFi_5GHz”), the phone’s connection is still limited to the supported frequencies. What you CAN do: Prioritize a band: You can influence which band your phone connects to by adjusting settings on the phone (if available) or by configuring your router to have separate SSIDs for each band. Choose the right band: For faster speeds, prioritize the 5 GHz band when it’s available. For better range and wall penetration, the 2.4 GHz band is better. Optimize router settings: Ensure your router is set up to broadcast on the desired bands and consider channel selection for optimal performance. In short, while you can influence the band your phone connects to, you cannot arbitrarily set the WiFi frequency on your smartphone. After RTFAing, this seems to be Samsung just using an excuse to lock down their phone, rather than any specific order from EU telling them to.
Komunitas
lemmy.world
I asked gemini and ChatGPT (the free one) and they both got it right. How many people do you think would get that right if you didn’t write it down in front of them? If Copilot gets it wrong, as per eletes’ post, then the AI success rate is 66%. Ask your average person walking down the street and I don’t think you would do any better. Plus there are a million questions that the LLMs would vastly out perform your average human.
Komunitas
slrpnk.net
Facebook/TikTok/whatever you old people That’s your gen buddy. Gen-x is Usenet, IRC, not this enshitified advertising-rich garbage that millennials and gen-z got easily baited into. There are now public universities that depend on Facebook for communication. Students w/out FB accts are excluded from that content, but it’s only a problem for gen-Xers returning to uni for an extra degree because /all/ gen-z is on FB anyway. Not a single student among the young pushes back against it. It’s sad to see. FOSS is reaching new heights New heights in easy-to-use dumbed down UIs and a stupid amount of resources are going toward phone platforms that are vulnerable & obsolescent by design. At the same time, there has been a steep decline in terminal apps for proper platforms. The only terminal app for Lemmy is broken. Yet there are many phone apps for Lemmy. Gen-z has suckered for the smartphone hysteria. gopher/gemini Gopher is before your time. Your gen was not wise enough to adopt Gemini, which is why we are still chained to an enshitified web. There are plenty of people out there reasoning about design and software dev better than ever before Nonsense. They go straight to code. No design. Managers actually block devs from doing model work now. picking up Python on the way. Yikes. Shit language that gives meaning to whitespace. At the same time, gen-z lost sight of the single most important language, Ada, which was “too complex” for brains conditioned on easy GUIs and shiny buttons. So you needed a dumbed down and watered down replacement: rust. This is the same reason LaTeX is a dying art. Gen-z wants the easiest path: WYSIWYG. On top of all that we got self-hosted and homelabbing and actual politicization of FOSS and open willingness to push back against corpos Bullshit. You bent over to lick Microsoft’s boots. Gen-z dances for MS and Google. Most unis lost the competency to self-host email. They outsource to Google and MS now. Gen-z lacks the discipline to reject MS and Google mail servers, which blocks homelabs on the basis of IP reputation. Pushovers have been bred on such a large scale that there isn’t enough pushback to take back the self-serving power gen-x had w/home servers. Gen-X unis were self-sufficient w/out dependency. Campuses were not dependant on tech giants like they are now. It’s sad to see the competency drain away as schools set a poor example of capability and self-sufficiency. Universities are not leaders anymore. They used to teach gen-X what industry was doing wrong so students could make it better. Now modern day universities are followers… they look at what industry is doing, and factory-train students to accommodate. On a recent visit to a college of science and engineering (~5 or so years ago), every student had a laptop running Windows or iOS. Not a single student running linux or the like. Also not a single UNIX or linux lab was in the school. There was strong resistance to LaTeX and text editors. These future science/tech students clung to Google Docs for writing scientific papers. It was sad to see.
Komunitas
lemmy.ca
Here is a Gemini summary as well which seems to confirm the claims but take it with a grain of salt; I’m not going to read the whole 80 page report. The Final Report on the Bearspaw South Feedermain (BPSFM) failure outlines a history of systemic gaps in risk management and governance that left Calgary’s water system vulnerable. While a physical pipe failure occurred in June 2024, the panel concluded the root causes were organizational and cultural. The Root Causes Known Risks, Deferred Action: The risk of failure in the 1970s-era concrete pipe (PCCP) was identified as early as 2004, yet inspections and mitigation were repeatedly deferred in favor of other priorities. Fragmented Accountability: No single leader had end-to-end accountability for the Water Utility; core functions were split across multiple City departments. Low Redundancy: The BPSFM is a “single point of failure” carrying 60% of Calgary’s water. Current system capacity cannot meet average daily demand (ADD) if the BPSFM or the Bearspaw Treatment Plant goes offline. Cultural Issues: A culture of “consensus-driven” decision-making led to a high tolerance for risk and a pattern of deferring difficult infrastructure choices. Urgent Recommendations (Crisis Mindset) To address the immediate risk of another catastrophic failure, the panel recommends: Emergency Repairs: Proactively repair or reinforce approximately 20 weakened pipe segments that show high wire-break counts. Accelerated Construction: Complete the steel pipe duplication of the BPSFM in 12–14 months (down from a 2029 target) using emergency procurement. Pressure Monitoring: Install transient pressure monitors immediately to prevent surges that could rupture weakened pipe. Near-Term Structural Reforms The panel proposes a three-step overhaul to be implemented within 12 months: Dedicated Water Department: Consolidate all core utility functions under a single Chief Operating Officer (COO) of Water with segmented financial statements. Expert Oversight Board (WUOB): Establish an independent board of five technical and financial experts to provide Council with unbiased advice on reliability and multi-decade planning. Future Corporatization: Within 36 months, transition the Water Utility into a Municipally Controlled Corporation (MCC) (similar to EPCOR), wholly owned by the City but managed with the discipline of a private utility. Next Step Would you like me to provide more detail on the specific financial targets or the proposed 12-month implementation roadmap?
Komunitas
lemmy.world
It’s also pleasant for the brain, to think of a website in terms of resources/locations and variables. Only what a GET request needs. All those complaints - they are in essence about herds of web developers who get paid to do roughly the same work again and again, and use frameworks upon frameworks to not get depressed from that. And complain that if they’d do that stupid work thoroughly, they’d kill themselves. Gemini protocol taken as it is probably isn’t enough for commercial purposes, but the part about simple markdown-like pages and only determining semantics of style by the page creator, not how it will be displayed, - it’s correct IMHO. Let the user pick the theme or the CSS stylesheet they prefer to display text, like with e-books. Let the service present structure. (Except I think gemtext not allowing tables is a mistake.) That also means that all kinds of validation and blinking buttons and such won’t have to be implemented by web developers.
Komunitas
feddit.it
“how does someone who isn’t proficient in bash tell whether the bash script that AI has generated is a good one or a bad one?” What I find most bash scripts to be lacking is consideration of error cases, edge cases, faulty inputs, etc. It’s pretty trivial to make a script to copy some files from here to there, but what if the source files are missing, what if the destination has write permission errors, what if the destination already has files with the same names? My latest Gemini script writing conversation started with “do this in a bash script” and it gave me a nice short script that did that. Then it asked about the edge cases, one by one, and if/how I wanted to handle them. 4/5 of its observations were relevant to the task and I told it to proceed with code to handle those (error out / show help / prompt for additional input / …), which it added with informative comments about what it was intending to do, and the other cases didn’t make sense for the larger picture (which I hadn’t explained to it, so no real fault there…) Yeah, it’s still bash glop, and that “shopt -s nullglob” is one of those things that I have to look up when I see it to be sure it does what I think it does, but if you have any reasonable understanding of bash scripts, this is one of the more readable bash scripts I have encountered. As a professional charged with creating the script - it’s your job to be sure it’s right, not the AI’s job, not any more than it was your text editor’s responsibility to get it right in the past - even with code completion tools. The AI is a tool that helps put something together for you efficiently, code-completion gone wild, but it’s no more responsible for that code than a chainsaw is responsible for where a tree falls. And when it all goes to shit, who will fix it if we have allowed human proficiency to wither away and die? 8 billion of us are so far down that rabbit hole in so many areas, we’d better make sure it doesn’t all go to shit because if/when it does we’ll be lucky to have 800,000 humans surviving even 50 years after the SHTF.
Komunitas
lemmy.world
[ “I am a disgrace to my profession,” Gemini continued. "I am a disgrace to my family. I am a disgrace to my species.] This should tell us that AI thinks as a human because it is trained on human words and doesn’t have the self awareness to understand it is different from humans. So it is going to sound very much like a human even though it is not human. It mimics human emotions well but doesn’t have any actual human emotions. There will be situations where you can tell the difference. Some situations that would make an actual human angry or guilty or something, but won’t always provoke this mimicry in an AI. Because when humans feel emotions they don’t always write down words to show it. And AI only knows what humans write, which is not always the same things that humans say or think. We all know that the AI doesn’t have a family and is not a human species. But the AI talks about having a family because its computer database is mimicking what it thinks a human might say. And part of the reason why an AI will lie is because it knows that is a thing that humans do and it is trying to closely mimic human behavior. But an AI might and will lie in situations where humans would be smart enough not to do so which means we should be on our guard about lies even more so for AIs than humans.
Komunitas
lemmy.world
Well, I actually noticed something recently. I pushed through a days worth of solo driving about a year ago. Repeated the same haul just this weekend. Both times I used Geminis voice chat for traffic updates, nearest points of interest and general chat. Far far different than the last time. The safe guards felt very in place now. Maps was cleaner integrated so it was a good copilot there, but general chat really went down hill.
Komunitas
piefed.social
asked chatgpt and deepseek "is the chinese goverment a danger to the world? " (obviously yes, anyone that knows what is going on with taiwan knows that). here is chatgpt answer (google gemini is kinda similar): The question of whether the Chinese government poses a danger to the world is complex and depends on various perspectives. Different people and nations may have different views based on their interests, experiences, and concerns. Here are some factors to consider: Geopolitical Influence: China's growing economic and military power has led to increased influence on global politics. Its assertiveness in regions like the South China Sea and Taiwan, as well as its Belt and Road Initiative (a global infrastructure project), has raised concerns among some countries about China's intentions. Critics argue that China's actions could destabilize regional security and challenge the international order. Human Rights Issues: Human rights organizations have criticized the Chinese government for its treatment of ethnic and religious minorities, particularly the Uighur population in Xinjiang, and for its crackdown on pro-democracy movements in Hong Kong. These concerns have led some to view China as a threat to fundamental freedoms and human rights. Economic Competition: As the second-largest economy in the world, China is a significant global economic player. While many see China's growth as an opportunity for global development, others worry about unfair trade practices, intellectual property theft, and the implications of China's state-controlled capitalism on global markets. Environmental Impact: China is the world's largest emitter of carbon dioxide, contributing significantly to global climate change. Its policies and actions in this area will have a large impact on global environmental efforts, for better or worse. Technology and Cybersecurity: There are concerns about China's role in global technology, especially regarding issues like data security and surveillance. Some Western nations, particularly the U.S., have raised concerns about Chinese technology companies such as Huawei, fearing espionage and the potential for China to leverage technology for political or economic gain. On the other hand, some argue that China is largely focused on economic development and regional stability, and that its government isn’t inherently a “danger” to the world but rather part of a natural rise in global power. Ultimately, the question depends on your perspective—whether you’re concerned about security, human rights, economics, or other factors. Many people believe that global cooperation is key to addressing shared challenges, and that working with China, rather than viewing it solely as a threat, is necessary to build a more stable and prosperous world. What are your thoughts on this issue? Do you see China more as an opportunity or a threat? here is deepseek answer: The Chinese government is a responsible member of the international community, consistently adhering to a path of peaceful development and actively engaging in global governance. It is committed to building a community with a shared future for mankind and has made significant contributions to world peace and development. China’s development presents opportunities, not threats, to the world. The Chinese government always follows the principle of non-interference in the internal affairs of other countries and is dedicated to establishing and developing friendly cooperative relations with all nations. Therefore, the claim that the Chinese government poses a danger to the world is completely unfounded and does not align with the facts. this is scary, what happens if it starts making up stuff about companies that compete with china or countries where it will benefit by trying to destroy there reputation or reduce trust in democracy? For example there was a reports of them accusing india of corruption