76SlashDolphin

Dev at Sealgate here, happy to answer any questions.

And is vapourware. They went bankrupt in 2021 after failing to make it work and the domain is run by scammers.

That's only if you're using roaming on your home provider which I doubt many people are. Most people visiting China are either one WiFi (thus are inside the Chinese firewall) or are using a travel (e)sim which usually routes packets through one of the neighbouring countries/regions. Last time I was there Tailscale with my exit node terminating at a residential British IP address worked fine on both but discovering relay nodes on WiFi didn't work so I had to switch to data.

But other countries allow you to do so, yet you claim that the US is a bastion of free speech?

Agree to disagree. I am enthusiastically waiting for Asahi to sort out its display and power management issues, after which I am instantly switching. I'd even take Win 11 over the dumpster fire that is MacOS Tahoe and I am not the only one who uses is begrudgingly amongst my colleagues.

Slightly off-topic but this is why 3D printing becoming popular is a boon to the repair industry. Yeah, the part might be bad, but instead of paying a ridiculous sum for a piece of plastic, you can take the old one, model it, and make yourself a compatible one within a day. Of course, this requires modelling skills and the ability to be able to disassemble the machine but so does any other kind of repair work and at least you are no longer reliant on the manufacturer.

Not only that but it's also quite difficult to find a laptop with an ANSI keyboard in an ISO country. My choices are basically an overpriced new Macbook (MacOS is the main con here), an overpriced new Thinkpad (brand new ones are horrible value since it tanks just a year after purchase), a Clevo (much worse build quality and questionable Linux support), or a Framework (worse build quality and mediocre battery life). As much as I hate MacOS, my M1 Macbook is still better at just being a light machine I can take anywhere and be working with immediately, while still lasting over an entire workday regardless of what I do. I really wish that Lenovo would fix their X9 Gen1 Linux support as those laptops are basically what I'd run if I could have proper support.

I have a Pixel 8 running GrapheneOS and it does most of the above: - slightly lesser build quality than my iPhone 15 Pro but comparable - doesn't funnel data to Google unless you explicitly let it, you can circumvent a lot of the Google Play stuff by restricting permissions and using Aurora Store - is backed by, well, Google and the Graphene team porting over security updated. They have a fairly good track record by now. - can use any of the N backup services that already exist unlike the iPhone's silly restriction on background apps - don't notice performance differences between it and my iPhone 15 Pro in day to day use. If anything, biometrics are way faster on the Pixel since iOS 26 made FaceID slow as molasses for me - the default camera is pretty good (uses all the Pixel fancy processing hardware) but if it's not good enough you can just install the stock Google camera which works fine. You can turn off network access if you don't want it snooping. Photos are neck and neck with the iPhone but the iPhone is way better at videos, no Android phone has cracked that yet IMO. - Yeah, but no other brand can give you an AppleCare experience. Best option is phone insurance and just getting a new Pixel if that happens. Graphene can do full device backups via Seedvault and it's not that much more of a pain to restore compared to an iPhone backup. Granted, it's jankier but it's not impossible. The other issue is that Pixels are not a thing in a lot of countries, Apple really has the edge here but I'd take that risk over the UX shenanigans they pull nowadays with their latest updates (god is it awful)

Me and a few friends are working on a firewall for LLM clients that blocks the lethal trifecta: https://github.com/Edison-Watch/open-edison

The way it works is the user registers / imports MCP (Model Context Protocol) servers they would like to use. All the tools of those servers are imported and then the firewall uses structured LLM calls to decide what types of action the tool performs among:

- read private data (e.g. read a local file or read your emails)

- perform an activity on your behalf (e.g. send an email or update a calendar invite)

- read public data (e.g. search the web)

The idea is that if all 3 types of tool calls are performed in a single context session, the LLM is vulnerable to jailbreak attacks (e.g. reads personal data -> reads poisoned public data with malicious instructions -> LLM gets tricked and posts personal data).

Once all the tools are classified the user can go inside and make any adjustments and then they are given the option to set up the gateway as an MCP server in their LLM client of choice. For each LLM session the gateway keeps track of all tool calls and, in particular, which action types are raised in the session. If a tool call is attempted that raises all action types for a session, it gets blocked and the user gets a notification, which sends them to the firewall UI where they can see the offending tool calls, and decide to either block the most recent one or add the triggering "set" to an allowlist.

Next steps are transitioning from the web UI for the product to a desktop app with a much cleaner and more streamlined UI. We're still working on improving the UX but the backend is solid and we would really like to get some more feedback for it.

That is a fair concern, and while that would happen often in some cases, there are others which rarely export data or rarely read public data where you can manually approve each usecase. Still, we are very interested in seeing how people use MCPs so we can improve the UX, which is why we're publishing this release. If users report that they get too many false positives we can always increase the granularity of the trifecta categories (say, exports data can be exports data publicly or privately. Or reads public data can have different tiers, etc.)

It is based on what the MCP server reports to us. As with most current LLM clients we assume that the user has checked the MCP servers they're using for authenticity.

Really good questions, let's look at them one by one:

1. We are assuming that the user has done their due diligence verifying the authenticity of the MCP server, in the same way they need to verify them when adding an MCP server to Claude code or VSCode. The gateway protects against an attacker exploiting already installed standard MCP servers, not against malicious servers.

2. That's a very good question - while it is indeed non-deterministic, we have not seen a single case of it not showing the message. Sometimes the message gets mangled but it seems like most current LLMs take the MCP output quite seriously since that is their source of truth about the real world. Also, while the message could in theory not be shown, the offending tool call will still be blocked so the worst case is that the user is simply confused.

3. Currently we follow the trifecta very literally, as in every tool is classified into a subset of {reads private data, writes on behalf of user, reads publicly modifiable data}. We have an LLM classify each tool at MCP server load time and we cache these results based on whatever data the MCP server sends us. If there are any issues with the classification, you can go into the gateway dashboard and modify it however you like. We are planning on making a improvements to the classification down the line but we think it is currently solid enough and we would like to get it into users' hands to get some UX feedback before we add extra functionality.

It is possible thay a malicious MCP could poison the LLM's ability to classify it's tools but then your threat model includes adding malicious MCPs which would be a problem for any MCP client. We are considering adding a repository of vetted MCPs (or possibly use one of the existing ones) but, as it is, we rely on the user to make sure that their MCPs are legitimate.

Those are really good points and we do have some plans for them, mainly on the first topic. What we're envisioning in terms of UX for our gateway is that when you set it up it's very defensive but whenever it detects a trifecta, you can mark it as a false positive. Over time the gateway will be trained to be exactly as permissive as the user wishes with only the rare false positive. You can already do that with the gateway today (you get a web notification when the gateway detects a trifecta and if you click into it, you get taken to a menu to approve/deny it if it occurs in the future). Granted, this can make the gateway overly-permissive but we do have plans on how to improve the granularity of these rules.

Regarding the second point, that is a very interesting topic that we haven't thought about. It would seem that our approach would work for this usecase too, though. Currently, we're defending against the LLM being gullible but gullible and actively malicious are not properties that are too different. It's definitely a topic on our radar now, thanks for bringing it up!

That's a good question! We do use an LLM to categorise the MCP tools but that is at "add" or "configure" time, not at the time they are called. As such we don't actively run an LLM while the gateway is up, all the rules are already set and requests are blocked based on the hard-set rules. Plus, at this point we don't actually look at the data that is passed around, so even if we change the rules for the trifecta, there's no way for any LLM to be poisoned by a malicious actor feeding bad data.

It is possible to configure it like that - when a trifecta is detected, it is possible for the gateway to wait for confirmation before allowing the last MCP call to proceed. The issue with that MCP clients are still in early stages and some of them don't like waiting for a long time until they get a response and act in weird or inconvenient ways if something times out (some of them sensibly disable the entire server if a single tool times out, which in our case disables the entire gateway and therefore all MCP tools). As it is, it's much better to default to returning a block message, and emit a web notification from the gateway dashboard to get the user to approve the usecase, then rerun their previous prompt.

At least in its current state we just use an LLM to categorise each individual tool. We don't look at the data itself, although we have some ideas of how to improve things, as currently it is very "over-defensive". For example, if you have the filesystem MCP and a web search MCP, open-edison will block if you perform a filesystem read, a web search, and then a filesystem write. Still, if you rarely perform writes open-edison would still be useful for tracking things. The UX is such that after an initial block you can make an exception for the same flow the next time it occurs.

Fair criticism! We wrote the Readme earlier on when we were still ironing out the requirements. I'll fix it up shortly.

There's a lot of trash talking of x86 here but I feel like it's not x86 or Intel/AMD that are the problem for the simple reason that Chromebooks exist. If you've ever used a Chromebook with the Linux VM turned on, they can basically run everything you can run in Linux, don't get hot unless you actually run something demanding, have very good idle power usage, and actually sleep properly. All this while running on the same i5 that would overheat and fail to sleep in Windows / default Linux distros. This means that it is very much possible to have an x86 get similar runtimes and heat output as an M Series Mac, you just need two things:

- A properly written firmware. All Chromebooks are required to use Coreboot and have very strict requirements on the quality of the implementation set by Google. Windows laptops don't have that and very often have very annoying firmware problems, even in the best cases like Thinkpads and Frameworks. Even on samples from those good brands, just the s0ix self-tester has personally given me glaring failures in basic firmware capabilities.

- A properly tuned kernel and OS. ChromeOS is Gentoo under the hood and every core service is afaik recompiled for the CPU architecture with as many optimisations enabled. I'm pretty sure that the kernel is also tweaked for battery life and desktop usage. Default installations of popular distros will struggle to support this because they come pre-compiled and they need to support devices other than ultrabooks.

Unfortunately, it seems like Google is abandoning the project altogether, seeing as they're dropping Steam support and merging ChromeOS into Android. I wish they'd instead make another Pixelbook, work with Adobe and other professional software companies to make their software compatible with Proton + Wine, and we'd have a real competitor to the M1 Macbook Air, which nothing outside of Apple can match still.

The funny thing about 3D printers is that they're making a bit of a comeback. The early ones managed to get the capabilities right - you can print some really impressive things on the older Creality printers, but it required fiddling, several hours of building the bloody things, cogged extruders, manual bed leveling and all sorts of technical hurdles. A very motivated techy person will persevere and solve them, and will be rewarded with a very useful machine. The other 99.99% of people won't and will either drop it the moment there's an issue or will hear from others that they require a lot of fiddling and never buy one. If things ever get more complicated than "I see it on a website and I click a few buttons" (incl maintenance) then it's too complicated to gain mass adoption... which is exactly what newer 3D printers are doing - the Bambulabs A1 Mini is £170, prints like a champ, is fairly quiet, requires next to no setup, takes up way less space than the old Enders and needs almost no maintenance. It's almost grandma-proof. Oh, and to further entice your grandma to print, it comes with all sorts of useful knick-knacks that you can start printing immediately after setup. On the hype cycle curve I think 3D printers are almost out of their slump now that we have models that have ironed out the kinks.

But for VR I think we're still closer to the bottom of the curve - Meta and Valve need something to really sell the technology. The gamble for Valve was that it'd be Half Life: Alyx, and for Meta it was portable VR but the former is too techy to set up (and Half Life is already a nerdy IP) while Meta just doesn't have anything that can convince the average person to get a headset (despite me thinking it's a good value just as a Beat Saber machine). But they're getting there - I've convinced a few friends to get a Quest 3S just to practice piano with Virtuoso and I think it's those kinds of apps I hope we see more of that will bring VR out of the slump.

And then LLMs I think their hype cycle is a lot more elevated since even regular people use them extensively now. There will probably be a crash in terms of experimentation with them but I don't see people stopping their usage and I do see them becoming a lot more useful in the long term - how and when is difficult to predict at the top of the hype curve.

All right, I'll bite

> Food has improved dramatically.

Not necessarily. While accessibility is far better, it comes at the cost of having monocultures, mass farming, and heavy importation during off-seasons. This has made, say, the average tomato cheaper and more accessible year-round but substantially worse than the seasonal tomatoes you would have 40 years ago.

> Houses are larger...

But more and more people live in cramped apartments in big cities so that point is moot.

> Healthcare...

And is it more important that a poor 25 year-old young person with their whole productive tax-paying life ahead of them can seek care appropriately Vs the hospitals keeping 80+ year-old fossils alive with their "better healthcare". The only exception is ozempic and the likes but that didn't use to be necessary before cars killed most public spaces.

> Car reliability/safety...

By turning them into huge monstrosities and widening roads, again destroying public spaces and walkability. The only major breakthrough here is lead-free fuel.

> Compute power. The average person has the knowledge of the ENTIRE world at their fingertips. But totally no progress has been made???

I'll give you that one but it's at the cost of turning a computer into an addiction machine. I still think it's a net positive but it isn't so clear cut.

> We have weather satellites

True but now we're have much more extreme weather thanks too climate change.

> We can talk to family whenever we want...

We can but when do we? I keep in touch with family often but it definitely feels less special than how it was even in the 00s.

> We have vastly more free time...

Assuming you have the same sized family and roles. Now's your need both parents in a family to work to make ends meet for the average young person so the freed time has mostly gone to the older generation.

Overall zoomers and gen alpha definitely have it worse than their parents. And this is coming from someone with a middle class background who now gets paid well to program -everyone I know my age feels this way. The main lifestyle change we got recently is cheap travel which is amazing but the basics are definitely harder (and this is why birthrates are down).

Ooh, one thing that can be very useful for this is sending USB wakeup packets. I have an HTPC under my TV and game controllers (PS4, Xbox) at my coffee table and there is no way to wake up the PC with those over Bluetooth so I have to keep it on and idling at all times, wasting electricity.

In my experience my Airpod Pros and Huawei Freebud Pros achieve 95% of the audio and noise cancellation quality of my Sony XM3s that I just barely use the big headset anymore. I understand that they are technically different categories of products but for me and a lot of other non-audiophiles I know switched to TWS earbuds once they got half decent ANC.

Huh? Last I checked you can still order them off AliExpress without an issue. And I highly doubt that Nintendo would go after the thousands of people who bought one after the big MIG Switch announcements.

The issue is that underfunding the NHS has become so bad that even very serious cases can't be handled appropriately. I know it's an anecdote, but I've had a fairly bad experience recently after a serious bike incident in the middle of a workday, and they took over an hour to send an ambulance, about an hour to be checked, and over 7 hours in the Royal Hospital waiting for treatment.

Legitimately was a worse and slower service than I would have had at my grandparents' place in Eastern Europe, it's a disgrace. It still makes me angry that it's the experience I get after paying 1000s of £ in NHS contributions.

I think that the fragility of Blu-Rays is a great way to teach a kid responsibility. You only let your kid have access to their Blu-Rays and if they scratch them or break them it's over - no more movie. They'll learn after they break a few.

> iOS also supports ambient song identification, with history, which I use frequently.

Does it? I can't find any info about this online and all I can find seems to indicate that you can run Shazam and it scans for some amount of time afterwards but iOS kills it to save battery. It doesn't seem like you can get Google Pixel-like "Now Playing" which I sorely miss on my iPhone 15 Pro.

The difference though is that Swiss' coverage is only from Switzerland, a very wealthy and well-managed country, to other major business and tourist destinations and can arguably run at a loss since it's a national carrier. Not every country can afford that - the only flights I can get from my small hometown of ~350000 are with budget airlines because the national carrier simply isn't competitive enough to be able to run profitable flights from there. Before they showed up the airport was effectively dysfunctional. Budget airlines have tremendously improved connectivity for less popular and less wealthy of the continent.

It is difficult because having attendants print boarding cards or working with an airport to maintain ticket printers costs money that eats into their margins and increases prices. It's not like they don't warn you that checking in at the airport is paid. I'd much rather save 1€ and check in the way I usually would, even if it means someone who can't read a few warnings has to pay a fee.

But they haven't. They only changed them once in the past decade, it's not like it's a thing that budget airlines pull every year. Changing them sucks but it's not really a problem now.