321–329 of 329 posts
Earlier quoted context omitted.
Labor organization is the solution on the right. The left believes in regulation.
More rich person organization is the anti-solution on the right. Regulation sits somewhere in the middle.
Earlier quoted context omitted.
More rich person organization is the anti-solution on the right. Regulation sits somewhere in the middle.
Nah. Rich people don't exist, or at least cannot last long, without a moat, which is an idea from the left. In fact, taken to the extreme, the left outlaws property ownership so that a few rich people gain control of everything.
Earlier quoted context omitted.
Nah. Rich people don't exist, or at least cannot last long, without a moat, which is an idea from the left. In fact, taken to the extreme, the left outlaws property ownership so that a few rich people gain control of everything.
This is is the least senseful paragraph I’ve read this week.
Earlier quoted context omitted.
It is also illegal. Simply assuming that "every employer does it because theoretically it is easier for then to do so" to help your argument is rather self-serving, considering that labour unions are explicitly legal and exist.
It’s not theoretical.
You think you're thinking about reality.
All you're doing is imagining reality. You're living in a fantasy.
Earlier quoted context omitted.
It’s not theoretical.
Cynicism is such a waste of time when you haven't done the thing you're cynical about and have no first-hand experience. You think you're thinking about reality. All you're doing is imagining reality. You're living in a fantasy.
It’s news to me that what Adam Smith wrote about in that book was theoretical. Oh well.
Earlier quoted context omitted.
I’m finding that the code LLMs produce is just average. Not great, not terrible. Which makes sense, the model is basically a complex representation of the average of its training data right? If I want what I consider ‘good code’ I have to steer it. So I wouldn’t use LLMs to produce significant chunks of code for something I care about. And publishing vibe coded projects under my own GitHub user feels like it devalues…
We've gone from "it's glorified auto-complete" to "the quality of working, end-to-end features, is average", in just ~2 years. I think it goes without saying that they will be writing "good code" in short time. I also wonder how much of this "I don't trust them yet" viewpoint is coming from people who are using agents the least. Is it rare that AI one-shots code that I would be willing to raise as a PR with my name o…
Earlier quoted context omitted.
>The nice thing is a programmer with an LLM just steps in here, and course-corrects This does not seem to be the direction things are going. People are talking about shipping code they haven't edited, most notably the author of Claude Code. Sometimes they haven't even read the code at all. With LLMs the path of least resistance is to take your hands off the wheel completely. Only programmers taking particular care ar…
> When the code is constructed by an LLM, the human in the driving seat doesn't get a chance to build the mental models that they usually would writing it manually I'm asking the LLM for alternatives and options constantly, to test different models. It can give me a write-up description of options, or go spin up subagents to go try 4 different things at once. > It is widely considered to be harder to read code than t…
Only laggards are using MCP.
Everyone else is using skills to provide updating knowledge and cli tools for extra functionality.
100% Everything above discussed: solved with skills.md
It's hilarious watching all of you being academic about the recent invention of the wheel and acting like you're smart.
Earlier quoted context omitted.
And Unix was mainly made by two people, it's astounding that as I get older, even tech managers don't know "the mythical man month", and how software production generally scales.
> And Unix was mainly made by two people Speaking of myths, they were part of a team of 4-5 early contributors with the benefit of network effects via Bell Labs.[0] [0] https://en.wikipedia.org/wiki/Unix#History
Earlier quoted context omitted.
> When the code is constructed by an LLM, the human in the driving seat doesn't get a chance to build the mental models that they usually would writing it manually I'm asking the LLM for alternatives and options constantly, to test different models. It can give me a write-up description of options, or go spin up subagents to go try 4 different things at once. > It is widely considered to be harder to read code than t…
you're all living in the past btw. Only laggards are using MCP. Everyone else is using skills to provide updating knowledge and cli tools for extra functionality. 100% Everything above discussed: solved with skills.md It's hilarious watching all of you being academic about the recent invention of the wheel and acting like you're smart.
Remind me how skills replace:
- authenticated access to remote/external systems
- sandboxed boundaries
- multi-step workflows that span multiple systems