hbogert

That's a bit rough. Would we say the same before AI? Bad docs so bad project? I guess people should realize that less is more, don't commit that bad README not even as placeholder.

with the context the creator just gave, this isn't actually a bad sentence, it just lacked, well, context.

mighty interesting, i scanned the nuances about the memory model, but it doesn't explicitly say so, but am I right that some workloads will result in heavy fragmented physical memory allocations?

I'm probably bad at counting, but what is the 3rd body?

Thank you for the ad hominems btw.

One of the criteria to be a problem wolf is to have wandered on a kids playground twice.

I think that's idiotic that the line is drawn only in cases like that

What a caricature of the 'we'.

You almost always get 'something' from your government even if i want it or not, call it subsidiaries or not, the moment i do, i forego my right to complain?

I indeed have an issue with rules enforced on EU level, which seem great on paper, but have negative implications on local level. Course correction takes ages. This is the typical distance to power concept.

you have to go back more than 100 years, but fair.

In those 100 years the rest of the environment changed, it's a bit of an experiment right to reintroduce it without having contingency plan if things go wrong, because shooting them if they are too aggressive is not allowed, unless they're marked as 'problem wolf'.

Oh don't get me wrong, I like the EU for many things, but course correcting is not its strong suit.

Very demeaning way of people making their livelihood.

> Wolves stay away from humans, there have been zero human deaths by wolves.

No they don't always stay away, plenty of confirmed stories. Just because there's no deaths yet, does it mean you can continue until it does happen? People have already been attacked.

The promise that the ecosystem would manage itself and wolves would just pick the least fit of the herd. It's shown they just like to kill for the thrill. There are cases of 30 sheeps per night in one site. 'Just Place fences' is a common heard thing, however wolves are smart and will just jump over or dig underneath. If you want to make a proper barrier with concrete is just practically unaffordable for the farmers.

Well I guess we differ there then, I do like not having to carry a rifle or sprays when i walk outside (we are not allowed). I also like livestock and kids not having to fear a predator that we drove to the outskirts.

I do wonder where you live in the Netherlands and if you just find it convenient to talk about the rural parts without having to face the consequences.

Ah yes the nice EU experiment where it uses the Netherlands for as their experimentation grounds. The goal of having more wild life is lofty, but it makes no sense in the netherlands . For the people who don't know, there weren't wild wolves up to 2015. There now are many and they've attacked people, horses and wiped out complete herds of sheep. The amount of sheep they are killing is increasing exponentially. (not using exponentially lightly here.) Proponents during the 2015-2020 era said that it would never come to this situation, alas.

Rhetoric questions by proponents as seen on national news website[1]:

> We hebben ook weleens last van de mens, die schieten we toch ook niet af?

> -- Aaldrik Pot

Translated:

"We also have issues with people every now and then, were not shooting them are we?"

[1]: https://nos.nl/artikel/2245512-waarom-willen-we-eigenlijk-wi...

Yep, it's 8GB vram from 2017 :D

Yeah simple, but menial refactors where IDEs don't have clear cut refactors yet. Or languages like CUE which has awesome tooling, but not so great refactors in its lsp yet.

yeah opencode just runs with it with lmstudio as llm engine.

It won't win benchmarks of course, but 20 tps generation is okay and letting it chug away on my local kubernetes cluster to troubleshoot is pretty nice. First start is pretty slow though, parsing is around 100-200 tps. Which is crap for long questions or harnesses like opencode which start around with thousands of tokens. Once cache is warm, pretty enjoyable.

I think it could have way more use cases where it's just 'good enough'. Email categorization, voice commands for the home. 1 year ago this was still a very miserable experience, but qwen 9B + better cache quantization and more tricks in the latest llm engines makes it viable.

Will it do difficult architectural refactors by just giving a one-shot prompt like opus allows, nope, not gonna happen.

Shame they are not including old crap like my RX580 which is doing some impressive stuff with Qwen 9B Models.

It was a regression. Plenty people including myself used macbook airs to drive multiple screens when working behind a desk.

Have you played with a vector databases and have them explained yet? The grandparent comment is only explaining that concept.

Neuro symbolic, rly? Can you please elaborate what it is that made you conclude that?

Ah yes the m1 air for example which couldn't drive 2 external screens

They were buying mindshare, not gonna lie, i was only 10 back then and i instantly knew that intel has got to be better than all the others because they have MMX right?!..

older devices, is rather vague, this means intel client chips even as late as panther lake do not support avx512 or avx10

Yeah even qwen 3.5 9B on my VERY old RX 580 from 2017 can make sense of my homelab given a few crucial pointers in a agents.md. I think that's wild.

There's still confidentiality (encrypted transport) and authenticity of the server, how is that the same as null'd ipsec?

the even more soul crushing thing is to get the agent/claude to think in this atomic commits kind of thing. It just doesn't. At least opus doesn't IME. can you force it to do it after the fact, sure, still soul crushing to nudge it that way. Also it F's up branch-on-branch development style. I had to tell claude to use `git rebase --rebase-merges --update-branches`, add skills or memories you want, the hit ratio is abysmal.

I have this issue more often, if you want Claude to get off the beaten path, because you reallllly know a better way, memories just don't hit. In this case the agent instructions on how to get along with git is just too burnt into the agent it seems.

i felt this. My majority of time correcting claude is making it stop the stupid verbose doc comments which are completely contemporary. I can add skills/memories and claude.md hints that i want, but every time it continues with those unnecessary doc comments of 5+ lines explaining some situation which should definitely not be in a doc comment.

So you are a cog, you are a watchmaker, or you just want to read the time hoping that all these cogs will tell it. Software engineers are becoming line workers, it's okay, we had a good run. But realise we needed the press to give way for mass literacy and scientific revolution. Isn't anybody at least curious how our children will leapfrog us and what they'll do once agentic thinking is engrained in their thinking?

Probably at least half of the people reading this shudder at the above. But I thank the Lord my job has been never to typeset a press.

Leslie Lamport famously said that you should be thinking above the code. It doesn't mean you are on ly high level and handwavy. I think agents are making us unthinking above the code

corosync and pacemaker were my personal dark ages of distributed systems. With a well setup kubernetes clusters my faith is restored. Still not perfect but not a butt-crack sweating endeavor

Yeah that's what they all thought :P