Team scale doesn't tend to impact this that much, since as teams grow they naturally specialize in parts of the codebase. Shared libs can be hotspots, I've heard horror stories at large orgs about this sort of thing, though usually those shared libs have strong gatekeeping that makes the problem more one of functionality living where it shouldn't to avoid gatekeeping than a shared lib blowing up due to bad change set merges.
This was a follow-on to a study of nurses showing coffee drinkers have lower all cause mortality.
Caffeine has been shown to exert effects via adenosine receptor antagonism and influence on cAMP & AMPK pathways. These same pathways are implicated in a lot of issues with aging. Caffeine also has some anti-inflammatory properties and Coffee beans are a strong anti-oxidant though I don't really think that matters much.
> Caffeine has been shown to exert effects via adenosine receptor antagonism and influence on cAMP & AMPK pathways. These same pathways are implicated in a lot of issues with aging.
That is like saying biological pathways are implicated in aging (because you said "pathways").
In any case, adenosine receptor antagonism has a pretty weak link if any to aging.
Additionally, we say that about virtually everything that is herbal, that it has anti-inflammatory properties. You are right, it does not matter at all.
The Bun acquisition made a little sense, Boris wanted Daddy Jarred to come clean up his mess, and Jarred is 100% able to deliver.
This doesn't make as much sense. OpenAI has a better low level engineering team and they don't have a hot mess with traction like Anthropic did. This seems more about acquiring people with dev ergonomics vision to push product direction, which I don't see being a huge win.
They do have a hot mess with traction amongst developers. Codex is far behind Claude Code (in both the GUI and TUI forms), and OpenAI's chief of applications recently announced a pivot to focus more on "productivity" (i.e. software and enterprise verticals) because B2B yields a lot more revenue than B2C.
I've been trying to beat this drum for a minute now. Your code quality is a function of validation time, and you have a finite amount of that which isn't increased by better orchestration.
And when the PR you never even read because the AI wrote it gets bounced back you with an obscure question 13 days later ..... you're not going to be well positioned to respond to that.
Skills are just prompts, so policy doesn't apply there. MCP isn't giving you any special policy control there, it's just a capability border. You could do the same thing with a service mesh or any other capability compartmentalization technique.
The only value in MCP is that it's intended "for agents" and it has traction.
Github is on the chopping block as a tool (it's sticky as a social network). The other stuff not so much.
The things that are going away are tools that provide convenience on top of a workflow that's commoditized. Anything where the commercial offering provides convenience rather than capabilities over the open source offerings is gonna get toasted.
Even at recent levels of uptime I think it would be very difficult to build a competing product that could function at the scale of even a small company (10 engineers). How would you implement Actions? Code review comments/history? Pull requests? Issues? Permalinks? All of these things have serious operational requirements. If you just want some place to store a git repository any filesystem you like will do it but when you start talking about replacing github that's a different story altogether and TBH I don't think building something that appears to function the same is even the hard part, it's the scaling challenges you run into very quickly.
The future is narrow bespoke apps custom tailored for exactly that one single users use case.
An example would be if the user only ever works with .jpg files, then you don't need to support any of the dozens of other formats an image program would support.
I cannot stress enough how many software users out there are only using 1-10% of a program's capability, yet they have to pay for a team of devs who maintain 100% of it.
"The future" is fiction. It's a blank canvas where you can make a fingerpainting of any fantasy you like. Whenever people tell me about "the future" I know they're talking absolute rubbish. And I also like your fantasy! But it probably won't happen.
I call it "Psychics for Programmers." People will scoff at psychics and fortune telling and palm reading, but then the same people will listen to Elon or some founder or VC and be utterly convinced that that person is a visionary and can describe the future.
It's just reading the room. People hate having to use their computers through the lens of quasi-robot humans (saying that as one of those robots). They hate having to pay monthly just so dumb features and UI overhauls can be pushed on them.
They just want the software to do the few things they need it to do. AI labs are falling over themselves to remove the gate keeping regular people from using their computing device the way they want to use it. And the progress there in the last few years is nothing short of absolutely astounding.
> the progress there in the last few years is nothing short of absolutely astounding
Yet, all the astounding progress notwithstanding, I don't have a suite of bespoke tools replacing the ones I depend on. I cannot say "hey claude, make me a suite of bespoke software infrastructure monitoring and operational tooling tailored to my specific needs" and expect anything more than a giant headache and wasted time. So maybe we just need to wait? Or maybe it's just not actually real. My view is unless you show me a working demo it's vaporware. Show me that the problem is solved, don't tell me that it might be solved later sometime.
And what exactly is preventing you from building bespoke software for "infrastructure monitoring and operational tooling tailed to your specific needs"?
I could certainly imagine building myself some sort of dashboard. It would seem like a prime use case.
You want to hear about a problem solved? Recently I extended a tool that snaps high resolution images to a Pixel art grid, adding a GUI. I added features to remove the background, to slice individual assets out of it automatically, and to tile them in 9-slice mode.
Could I have realistically implemented the same bespoke tool before AI? No.
> And what exactly is preventing you from building bespoke software for "infrastructure monitoring and operational tooling tailed to your specific needs"?
Let's say I emit roughly 1TB of telemetry data per day--logs, metrics, etc. That's roughly what you might expect from medium sized tech company or a specific department (say, security) at a large company. There is going to be a significant infrastructure investment to replicate datadog's function in my organization, even if I only use a small subset of their product. It's not just "building a dashboard" it's building all the infrastructure to collect, normalize, store, and retrieve the data to even be able to draw that dashboard.
The dashboard is the trivial part. The hard part is building, operating, and maintaining all the infrastructure. Claude doesn't do a very good job helping with this, and in some sense it actually hinders.
EDIT: I'm not saying you shouldn't take ownership of your telemetry data. I think that's a strategically (and potentially from a user's perspective) better end result. But it is a mistake to trivialize the effort of that undertaking. Claude is not going to vibeslop it for you.
I agree, that does not seem like a smart undertaking. I was thinking more of a dashboard within the existing software, or above it.
For my use case I wanted bespoke software to work with Pixel art, but obviously I would not try to build Photoshop or Aseprite from scratch. I needed only specific functionality and I was able to build that in a way fitting my workflow better than any existing software could.
I was able to build it with Claude Code and Codex. Maybe the implementation is sloppy, I did not care to check. The program works, and it's like a side project to my side project. It would not have been possible in the past, I would have needed to work with what Aseprite offers out of the box.
1. People don't want to switch frameworks, even though you can pull prompts generated by DSPy and use them elsewhere, it feels weird.
2. You need to do some up-front work to set up some of the optimizers which a lot of people are averse to.
reply