snowstormsun

Hell no

Is it April 1st already?

Amazing idea! Need to try that.

It feels like constant stop and go traffic, even with multiple agents.

Well, the 10x promised revenue increase must come from somewhere...

Who's going to maintain all the cheap code and review it? Is the "software janitor" job title becoming reality now?

Surely this won't be a security nightmare.

it's even worse than that! bots are doing it as well

I am using this every day, such a useful little tool!

If you want the best engineers, you also need to be the best employer.

> Now, in many cases, LLMs can handle the "how" for you. You describe what you want in plain language, and the system works like a programmer or system analyst: breaking your problem into building blocks, mapping a flow to solve it, and creating the first version.

People keep saying things like this, but what's an actual example of a viable product created that way? Talk is cheap, I want to see it.

2027

Don't worry, it will go away once the stock market plunges.

Somehow this text looks suspiciously clean, as if it was generated ;)

The problem probably more often just is that the product/vision itself is not as good as it is sold to shareholders. No PM will like to push back on this, so they're stuck with things like optimizing the landing page because "clearly the business vision is flawless, it must be that users don't understand it correctly".

Redundant Backups

So who will be held accountable if things break? "Sorry dear customer, it's not our fault, this code was AI generated and it worked in our tests."

Using tfidf or bm25 would actually be simpler than a vector search.

I understand this is just for fun, just wanted to point that out.

Nice idea, but this approach does not handle out of vocabulary words well which is one major motivation for using a vector-based search. It might not perform significantly better compared to lexical matching like tf-idf or BM25, and being slower because of linear complexity. But cool regardless.

MCP is practically useful, but the total lack of security in its "design" for me just underlines the type of YOLO-driven development and lack of quality that's being marketed as productivity improvement in software engineering too often these days.

In your comments history someone replied to a job posting "Just an FYI, if you do a takehome project for William, he won't respond to you (not even with an auto reject)."

Don't confuse cynical with realistic, though.

This article tells me much more about the author's type of character.

We are destroying software by letting non-technical people make technical decisions.

Very well said.

I predict Bluesky will add some form of targeted advertisements in the future once the user base has grown to a certain size. Isn't that obvious? I'd assume that's also why investors are willing to invest.

Nope

So, almost all servers running Linux around the world is just ignored by the author?

Just share it for free. Science doesn't work that way.