100%. I know I’m in the “get off my lawn” phase of my career when I see things like MCP and LangChain, but know I would have been excited about them earlier in my career.
LangChain is an objectively terrible Frankenstein's monster of an API. If you were a good developer in your youth, you'd have still held it in contempt, and treat MCP with caution.
The MCP API is pretty bad, too, it's just that a paradigm is starting to emege regarding modularity, integration and agentic tooling, and MCP happens to be the only real shot in that direction st this particular moment.
How is the MCP API bad? It uses simple and widely available standards-based transports while still allowing custom transport implementations, along with a simple API that can be used easily without any libraries, in any programming language under the sun?
Could you elaborate on your issues with LangChain?
We're kinda headed towards using it as it seems to be a flexible enough abstraction that is relatively stable to work with, so I'd like to know if I'm overlooking something..?
A big soup of untyped json blobs and python, all working highly asynchronously in complicated ways.
Is this variable available in my agent’s state?
Depends! Is it an agent that started an hour ago before you made that other change? Is it in the manager state or not? Did the previous agent run correctly or not? Did something else go wrong?
Eh, more the wider cultural effects of them. Vibe coding, everyone now creating kitchen sink apps that do everything under the sun, k8s everywhere, agents everywhere. It feels like a big part of the industry has lost all focus and is sprinting towards some endless vague panacea instead of focusing on solving specific well defined business problems.
It’s always been a bit like this but it feels particularly bad since AI hit mainstream coding tooling. Just my 2c :)
Or not even imagery collection, but testing to see what our response is like. If we're scrambling and unable to explain/contain it, that's useful for an adversary to know a little about our current defensive capabilities.
Or testing our own response. If we want to test what China's response might be, both public and military, but its too provocative to try, we might try it on ourselves.
This is all inevitable. At worst it's pulling the issues forward by a few months or years, and I don't think anyone will meaningfully address the problem until it's staring us in the face.
I believe the internet needs a distributed trust and reputation layer. I haven't fully thought through all the details, but:
- Some way to subscribe to fact checking providers of your choice.
- Some way to tie individuals' reputation to the things they post.
- Overlay those trust and reputation layers.
I want to see a score for every webpage, and be able to drill into what factored into that score, and any additional context people have provided (e.x. Community Notes).
There's a huge bootstrapping and incentive problem though. I think all the big players would need to work together to build this. Social media, legacy media companies, browsers, etc.
This also presupposes people actually care about the truth, which unfortunately doesn't always seem like the case.
He's not doing the nitty gritty engineering day-to-day, but he understands enough to ask the right questions, give his teams permission to try ideas that seem crazy at first, and sometimes come up with those ideas himself (e.x. supposedly catching Starship with "chopsticks" was his idea).
Not quite the same, but EMT conduit is very popular for shade structures at Burning Man and similar events. You can get fittings that will hold up very well in windy conditions (if properly secured) https://formandreform.com/blackrock-hardware/
I don’t think it’s at all unreasonable for an engineer using a device for 8+ hours every day to pay an additional, say, 0.5% of their income (assuming very conservatively $100,000 income after tax, $1,000 extra for a MacBook, 2 year product lifespan) for the best built laptop, best screen, and best OS.
I do networking stuff and macOS is on par with Windows - I can't live on it without running into bugs or very questionable behavior for longer than a week. Same as Windows.
What stuff is weird? I have so far had very good experiences with Apple (although not iOS yet). Almost everything I do on my Linux workstation works on Mac too. Windows though is beyond horrible and different in every way.
> I do networking stuff
Me too, but probably very different stuff. I’m doing p2p stuff over tcp and am affected mostly by sock options, buffer sizes, tcp options etc.
I like apple hardware, but their OS is fucking atrocious. In the year 2024 it still doesn't have a native volume mixer, or any kind of sensible window management shortcuts. Half the things on it have to be fixed with paid software. Complete joke of an OS, if it were up to me I'd stick a linux distro on top of the hardware and be happy
The OS is not a joke since it can do some stuff better than either Windows or Linux can but I completely agree that there are some serious limitations or omissions that should have been fixed.
I think they don't because they have an incentive to not do so: they get a cut on all the software you have to purchase on the App Store to make up for it.
It might not look like a lot, but if a large portions of Mac users need to buy a 5-10 bucks app to fix the windows management problems, it becomes serious money at 15-30% cut on millions of purchases...
And this is precisely the problem with Apple today. They are not honest enough to fix or improve the stuff they sell at a very high price, both because they sell it anyway and because they put in place many incentives for themselves to not do so.
There is the running meme of the iPad calculator but macOS could also use some care on the calculator/grapher not having received serious attention in decades. At the price they sell their stuff that would seem like a given, but considering they'll make money on the apps you buy to improve that situation, they'll never do so.
After using Apple App Stores for so many years, I wish I didn't, the convenience really isn't worth the cost down the road...
