Ex Novel Network MCNE, came here to say the same thing.

Sometime I wonder if any of the old protocols have new merit because of some other advance.

The safest car is one that is not driven, but that is not a useful measure. Put a car on the road and you add a driver, now you can start compare risk.

What?

The words you quoted start with the qualifier 'most', and that make it a true statement.

How many large github repos have no bugs, not many. How much succesful commercial software does not have a way to patch their code, not much.

Reporting bugs, patching systems, updating software is common to most software.

> Reporting bugs, patching systems, updating software is common to most software.

Yes, but this is a side-effect of trying to do good work and writing code that is understood and works.

When you ship sloppy, AI generated code, that no humans at the company have read and understood, you're missing the main part about engineering and are skipping straight to the life-support stage of the software, and you treat the (previously) side effect as your main job. Reporting bugs and shipping patches becomes your job, instead of engineering software, which happens to also come with that task.

I like your response, it's changed my mind a bit.

I expect people who are skillful and enjoy writing good code, are among those who dislike code generated with AI tools, and perhaps feel they have had a role or pleasure denied to them.

Those who write shit code, now feel that can produce vastly better software in a fraction of the time, and feel a sense of accomplishment.

I also use llama for 3d modelling (openscad) and have seen some similarly odd arrangement, but also very impressive and very good at part I would find boring or onerous.

However I can image a part, see it in my mind, rotate it, place it in context, and have an intuition about it.

Why? It's the same concept and root cause it was when we first started using it.

Hallucination is accurate for what I'm seeing -- e.g. it's making up information about the 2nd gen Toyota Tundra that has no basis in reality. When challenged, it corrects itself.

My colleague wanted to diagnose a specific error code on his car himself, and Gemini told him that it's simple to do with an OBD2 dongle - he asked it about the details thoroughly, to confirm, and bought the dongle.

It didn't work. Gemini: "Oh yeah, that obviously cannot work, it's not possible to do it through OBD2" (paraphrasing)

It was quite funny to me, but a bit less so to my colleague.

I've had many similar experiences. It's confidently incorrect to a shocking degree. Worse than ChatGPT from two years ago.

Its always been a bad term. If we wanted an accurate term then it's 'confabulation', but 'muddled' or just 'wrong' are also good.

What do we use for the “model made stuff up and claimed it as facts”? I can see hallucinations somehow anthropomorphizing LLM even more. I don’t like that we’re doing that to begin with but it’s a losing battle. I prefer “it’s broken” and “IT produced shit results” personally.

I agree with you, except I really don't hear that term much. People just say it wrong or confused. Good riddance, it was always a bad term.

They still happen.

Pace is a very commonly used term in projects to describe a rate of progress.

Its a software emulation of hardware modular. It good fun to noodle about with. Does provide a good experience of modular.

I live these types of posts. Everything is always changing. For keyboards ist keys, symbols and layouts. Who can imagine not having several modifiers and just not knowing how and when to use them.

I particularly enjoyed learning the origin of the symbols, for shift, enter tab and backspace and how they survived as text replaced their siblings. I wish we could have symbols for therefore and approximatly.

As someone who has designed and built a few keyboards, this was fascinating.

You're absolutely right.

You've found the load-bearing seam, and my explanation was worse than it actually is.

Ooh interesting. Sometime do the reverse at work, and ask AI to annotate the critical success factors of an imagined project. How did this company succeed where everyone failed. Reverse imaging.