makk

The creation of downstream issues has gotten faster, in my experience. The rate at which shit is thrown against walls has also gotten faster.

> But I'm finding it hard to actually do any of that.

Based on experience of someone in my family, I ask: are you and your doctor sure that the mood stabilizers themselves aren’t making that hard?

“Circling this territory for decades.” Try millennia. The world is filled with hungry ghosts. Ask a Buddhist.

Try using spec kit. Codex 5 high for planning; Claude code sonnet 4.5 for implementation; codex 5 high for checking the implementation; back to Claude code for addressing feedback from codex; ask Claude code to create a PR; read the PR description to ensure it tracks your expectations.

There’s more you’ll get a feel for when you do all that. But it’s a place to start.

Unlikely that working a job leads to making as much money as possible.

All for one and one for all.

And I’m for myself.

We should just call it engineering. We got better tools. Big whoop.

Be on their best behavior according to whom? Else what?

When will these geezers age out?

How frequently is a technical moat the thing that makes a business successful, relative to other moats?

These guys are pursuing what they believe to be the biggest prize ever in the history of capitalism. Given that, viewing their decisions as a cynic, by default, seems like a rational place to start.

I don’t understand the use of MCP described in the post.

Claude code can access pretty much all those third party services in the shell, using curl or gh and so on. And in at least one case using MCP can cause trouble: the linear MCP server truncates long issues, in my experience, whereas curling the API does not.

What am I missing?

> Overall, LLMs aren’t yet at the point where they can replace all engineers. But I don’t doubt they will be soon enough.

All engineers? This doesn't match my hands-on experience at all.

If you give a chainsaw to everyone, it doesn't make everyone a lumberjack. And a chainsaw itself certainly isn't a lumberjack.

If you give Claude Code or the like to everyone, it's doesn't make everyone a highly skilled software engineer. And Claude code itself isn't a highly skilled software engineer.

I've come around to this view. When I first began using these things for building software (the moment ChatGPT dropped), I was immediately skeptical of the view that these things are merely glorified autocomplete. They felt so different than that. These computers would do what I _meant_, not what I _said_. That was a first and very unlike any autocomplete I'd ever seen.

Now, with experience using them to build software and feeling how they are improving, I believe they are nothing more or less than fantastically good auto complete. So good that it was previously unimaginable outside of science fiction.

Why autocomplete and not highly skilled software engineer? They have no taste. And, at best, they only pretend to know the big picture, sometimes.

They do generate lots of code, of course. And you need something / someone that you can trust to review all that code. And THAT thing needs to have good taste and to know the big picture, so that it can reliably make good judgement calls.

LLMs can't. So, using LLMs to write loads of code just shifts the bottleneck from writing code to reviewing code. Moreover, LLMs and their trajectory of improvements do not, to this experienced software engineer, feel like they are kind of solution and kind of improvements needed to get to an automated code review system so reliable that a company would bet its life on it.

Are we going to need fewer software engineers per line of code written? Yes. Are lines of code going to go way up? Yes. Is the need for human code review going to go way up? Yes, until something other than mere LLM improvements arrive.

Even if you assume 100% of code is written by LLMs, all engineers aren't going to be replaced by LLMs.

It doesn’t feel like news, yeah.

I would emphasize, though, that getting clearly defined input _that remains stable_ is hard. Often something is discovered during implementation of a task that informs changes in other task definitions. A parallel system has to deal with this or the results of the parallel tasks diverge.

It hasn't homogenized everything. It's further exposed humans for who they are. Humans are the virus.

Yes, maximize cash and use it to acquire a diversified portfolio.

Explained for the layperson in the video cited here: https://news.ycombinator.com/item?id=44439593

> the European playbook

Reference?

And THAT, Smithers, is why we wear hardhats on the job.

Attachment leads to suffering. Always has, always will.

Those long held assumptions were held by people who aren't professional programmers, right?

Because, if you do what we do, it's obvious that language > math for most of this stuff.

I'd go so far as to say that music > math for programming.

Something related to wealth inequality rather than an absolute number.

> microservices written from scratch and interacting via cleanly defined APIs.

Introducing network calls because why? How about just factoring a monolith appropriately?

LGTM. Ship it.

As software engineering gets automated the demand for it goes _up_ because the problem spaces that were previously uneconomic to tackle become economic. We're going to see a further proliferation of software, and that's going to require care and feeding. So, now you need software engineers _everywhere_.

You could say, no, that's not how it's going to work because now everyone can just talk to a computer and get the software they want. But there's so many non-technical reasons why that doesn't put software engineers out of work. People are lazy and don't want to write (even if just by talking) their own software. People can't clearly describe what they want, so they won't be able to put to words the software they want. Most people just accept things as they are and don't think to change things with software.

What is clear is, if you're a run-of-the-mill, take-a-ticket work-a-ticket software engineer, with no interface to the business other than that, then yeah that shit is ripe to get automated away. But if you get out into the real world, man, it's the best time ever to have software engineering skills. Opportunities are _everywhere_.

> Anyone who doesn't understand the potential of AR simply lacks vision.

I see your point.

867-5309

3. Can the US endure at all when the current path feels unsustainable for most of its citizens?

As if those are the only two choices. And as if those choices are ones that most individuals can independently make.

I see your point. My points are that if one really wants to show respect then (a) don't waste people's time and (b) give them a respectable severance. If you can do (a) and (b) via a PIP process, then that's cool.

An even better token of respect is to just can the person and give them a respectable severance package, so they have months (plural) to find their next thing.