Yeah it should have a clever name like most opensource projects, preferably with a clever recursive acrynomyn. Maybe call it something like the "InfoBay Manipulation Analytical Computational Universal Network Technology."

I think the headline doesn’t convey the substance of the article

I see two reasons this could be: a) either it is by design, so people click and read it, or b) he couldn't figure out a good and short title that conveys the article. So in other words either clickbait or skill issue. :D (I'm just joking here!)

How do you recognize that from these sentences?

Yes. Except without attribution or record of provenance, and we get to charge you and everyone else arbitrarily for access! Are you excited now?

This is saying if you have a module with public functions A and B, they shouldn't call each other, right? But it's not saying that module A shouldn't call module B's public functions. That's what I thought it meant at first, but that seems crazy.

it is, but the question stays - is growing their training dataset by 10% going to make such significant difference that they are willing to actually pay money for it instead of stealing it?

I was that sysadmin at one job. Always catching praise, I'd say,

"Well, uh, if I had thought of that case, I would have fixed it in the first place."

The moment Musk said that my jaw dropped. I didn't follow the guy, knew he wasn't the genius he said he was, but that drove the final nail in my opinion. Fuck me, I can carely "code" PowerShell, but I know the goal is short, easy to read, elegant code. We're I working at Twitter at the time,

# This code creates the log file

# We're not going to check if it exists

# because we want to start with a fresh log each time this runs

# so we'll overwrite the old log, if there was one

# because we don't care in this case

$LOG_FILE = "C:\Scripts\Logs\Archive-Documents.log"

# Now we have a log file.

BAM! 9 lines from 1! I'm awesome!

Our findings suggest structural deficiencies in the ParticleDB QA process. Perhaps tests were not run prior to release. Perhaps the test suite was run, but failed to exercise basic functionality. Perhaps engineers entrusted Large Language Models with the work of testing.

God I miss the days when websites like this had completely free educational materials. I miss Webmonkey from 25 years ago.

You can tell it to be concise or terse.

Is "InfoBay" actually any better? Zero imagination

Ironically in this case the bug was in the MVC controller and fixed as part of a ports-and-adapters AOP audit implementation. MVC isn't immune to it. It was a controller endpoint calling another controller endpoint, because someone was doing a bit of business logic there rather than in the service.

Yes, had they implemented MVC properly they wouldn't have done that. Anyway your point is well taken but as it happens in this case, the deities of irony conspired against you today.

I think the headline doesn't convey the substance of the article, but this is spot on. I just ran into a small, fixable problem my developers had created by doing that just this week.

It was easily fixed, but it shouldn't have been done that way in the first place.

I don't disagree. There's a lot of pretty poor material out there. 😅

Could you expand on this ? I'm curious.

I don't think that's unique to LLMs though. Traditional learning material is very often like that too, and I actually find it worse because you can't ask it questions.

This is a community about programming, not slop.

Yeah I have to use it at work, so I use it to suggest improvements, explain why this or that wouldn't work, or when I'm tired of googling an error message that leads me nowhere.

It's hit or miss, sometimes it spares me hours of work, sometimes it just loops over dumb stuff.

It's an okay tool, it's interesting to know and understand, but I'm not too worried about it replacing me just yet.

The buggy interface in combination with .claude/ being mentioned in the .gitignore file.

The problem is that the bot doesn't know what people tend to be confused by, so I don't think it's a matter of the prompt. The verbosity itself isn't even really the issue; the clarity is the issue.

I, too, use LLMs all the time to explore spaces. I just strive to help people explore particular spaces more efficiently than they can with LLMs.

They just injected a much needed dose of industrial strength polymer into my personal backbone, and I thank them for it.

This can easily be resolved with a more direct default prompt. But I actually prefer the verbosity of the standard system prompts. It allows for much better exploration and learning opportunities.

You're right to push back -- that excerpt does resemble LLM produced text.