Criticisms of Go seem like they pivot on the author's understanding of what's being done with `_` and sometimes `nil`. It's a strongly-typed language with a lot of flexibility around type, and that's nice to have when working on edge systems like a data ingester.
I've had some luck creating tiny skills that produce summaries. E.g. a current TASK.md is generated from a milestone in PLAN.md, and when work is checked in STATUS.md and README.md are regenerated as needed. AGENTS.md is minimal and shrinking as I spread instructions out to the tools.
Part of my CI process when creating skills involves setting token caps and comparing usage rates with and without the skill.
> Unfortunately, AI does seem to be working very well, and I don't see great outcomes for us on the current trajectory.
The people decreasing headcount are already behind the curve. They're thinking about how many people they need to run things instead of how many people they need to reinvent an industry.
Yes, unfortunately. Each headcount, properly trained and reskilled, is now worth a whole team by themselves! I blame capitalism and the inability to look past the next quarterly earnings statement for what's happening instead.
I think in the (very) long run it will end up being for the best. This will force us lowly serfs to grow beyond our wage-labor mindset and leverage this force multiplier for ourselves.
AI lets those with capital get rid of labor, but by the same token(s ;-)) labor can now achieve outsize results without capital!
It is going to be very uncomfortable, but evolution always is.
From what I can see we're working as hard as we can to build them. You can watch the "let's put this on a Raspberry Pi and see what happens" seeds of Skynet develop in real time.
There's something compelling about helping assemble the machine. Science fiction was completely wrong about motivation. It's fun.
“This force multiplier turned all our devs into geniuses, so I fired half of them.”
I’m realizing that few of the people who get to make decisions understand the increased possibilities or the cognitive load that working with such a tool provides.
The people laughing at Gandhi were laughing at the hopelessness of his struggle, not the idiocy of his actions. A clown at the circus, made up to go on stage, doesn't need "First they laugh at you" rattling around in his brain.
Now that I think about it, that's kind of the basic idea behind Joaquin Phoenix' take on the Joker.
I'm using something that pops up an OAuth window in the browser as needed. I think the general idea is that secrets are handled at the local harness level.
From my limited understanding it seems like writing a little MCP server that defines domains and abilities might work as an additive filter.
I think he's referring to this part of the article:
> Dependencies should be updated according to your development cycle, not the cycle of each of your dependencies. For example you might want to update dependencies all at once when you begin a release development cycle, as opposed to when each dependency completes theirs.
and is arguing in favor of targeted updates.
It might surprise the younger crowd to see the number of Windows Updates you wouldn't have installed on a production machine, back when you made choices at that level. From this perspective Tesla's OTA firmware update scheme seems wildly irresponsible for the car owner.
reply