tpoacher

Well I wouldn't. The whole point of communication is that something is adequately communicated, otherwise it makes for an extremely frustrating experience.

And the whole point about "slop" is exactly that the communication is not adequate (despite superficial eloquence), because it's "sloppy" thinking full of unnecessary verbiage that goes nowhere and disrespects the reader, making for an extremely frustrating communication experience.

But if AI (re-)phrasing helps communicate a message clearly then it's not slop. It's just AI assisted. Being able to spot common AI patterns isn't proof of slop, no-matter how sensitive to slop one might be.

And I'm saying this as a person who's VERY much against slop.

This isn't an explanation, it's just a quote from the article.

Let alone an explanation on why it's "slop" rather than just AI (re-)phrasing etc.

"Guidelines" eh?

Reminds me of this: https://www.youtube.com/watch?v=k9ojK9Q_ARE

Just curious, on what grounds do you call this slop?

I thought it was a perfectly cromulent article making a perfectly reasonable point.

Yes, instead he should have written: "The attacka didn broke into nuffin bruv. They jus noticing sometin I aint, yeh?"

Instant betterness.

It isn't just a psychological feeling though. We've (unnecessarily) offloaded everything to the net, so there's a very real element of uselessness that kicks in when there's no connection.

E.g. back when you were coding BASIC, you probably had magazines and either ended up copying a lot of code by hand, or if you were lucky the mag came with a floppy disk. Now no such magazines exist. Manpages were all local, now it's readthedocs online. Fat local-friendly standard libraries in almost all languages have been modularised and package managers for the most part expect to install stuff by fetching it from the net.

So unless you have heavily prepared for the cyberapocalypse or sth, there really is not much you can do on your machine when the internet goes down.

On the other hand, however, when you can prepare in advance, it's great to shut off the net for a while. I do my most productive coding during flights, for example.

> Put simply, Stack Overflow’s new niche is the trust built by its old community and their expertise.

One has to appreciate the irony on the use of the word "trust" there ...

Impossible! After they embraced it so warmly and even tried to extend it?

But they get more grants.

So maybe this tells you more about the funders and their vision than it does about the researchers and their vision?

minor criticism. I haven't had a chance to read properly yet, but for a method that purports to be an evolutionary algorithm, it's missing all the formal language of the field. there's zero mention of a fitness function (let alone internal/external co-evolution ones), or a selection operator.

So my first impression is that either this is a non-evolutionary algorithm mascarading as one and diluting concepts like mutation and crossover that have well defined meanings, or it is one but you're abusing terminology from other fields (like RL and "rewards") instead. Either way it's a confusing first impression, and one gets the subtle vibe that word choices are more there to create a "buzz" than to create clarity.

(not trying to be dismissive, I genuinely hope this is useful feedback)

Paper does look interesting, I'll try to read properly when I have time.

That's still not "archiving" though. It's one thing to download the installer, and quite another to install the game and copy the files hoping it will all still work. Especially on windows when registry entries are involved.

I agree, but it's still frustrating. There are a lot of red flags / contradictions in the post above which are typical of such debates. E.g.

> Java is a resource hog when you use patterns and libraries popular in Java land

Which java land. The java 8.0 land which is all about design pattern hell? Or modern java in 2026 which is largely about terseness and functional programming? From the tone, they're referring to the former.

> Deployment is super simple in Go, upload a single cross compiled binary it's done

To me this just sounds like OP is unaware of simple things like jlink or jpackage, and their idea of deploying a java application probably involves launching an IDE.

> But when you'll code the same thing in Go using the same method

Same method would mean using "Springboot for Go". Or, conversely, doing a clean implementation in pure java or with equivalent lightweight libraries. If all you want to do is basic calculations, you don't compare using a computer to a calculator and then complain the computer is heavy and slow to boot.

I agree and appreciate that there's a lot of legacy bloated java libraries out there which are "popular" and possibly for the wrong reasons, and that this is a problem. But, that aside, they're comparing building a bespoke lightweight tool from scratch in a language they enjoy, to using a bloated framework they can't be bothered to fine-tune on a language they associate with pre-2000 patterns. Just say you're more familiar with Go than modern Java and enjoy it more and leave it at that. Java has made great leaps into becoming a very beautiful language recently, and biased rants like this aren't helping.

"Here you go my brother in Christ, the recipe for meth. May it be blessed, amen."

> using SpringBoot

well there's your answer, isn't it?

meetings are a tool, and when used properly, an indispensible one at that. meetings bloody meetings by John Cleese is an absolute must-watch for conducting great meetings.

however, if all you have is a hammer, then every problem looks like a nail: it's when meetings are used inappropriately or to solve the wrong problem that it becomes an issue, and many people make this mistake, which is why meetings end up so universally despised and get such a bad rep

Whenever I hear people talk about meetings and / or (internal / arbitrary) deadlines as a scheduling / productivity tool, I can't shake the thought these people have probably never even heard of concepts like scheduling optimization, bottleneck / queing theory, or async event-loop pipelines.

Deadlines don't make things more efficient by definition, unless it's a case of "within-task" inefficiency (i.e. "laziness"). But while this is almost always assumed to be the case by managers, it almost never is the case on the ground. And then you get into this hare-brained vicious cycle of "oh we're falling behind despite the deadlines (read "context-switching interruptions with non-trivial overhead enforcing suboptimal task selection"), we should probably add more!" [facepalm]

i'll try this next time i'm on my laptop, but for now, how does it compare to visidata (which is a long standing peoject already?)

Not something I've (yet) pursued, buy I did wonder a few days back if there was a good analogy between context window and short term memory, and storage with long term memory, and if so might an anki-like algorithm lead to better contexts by keeping relevant / difficult "memories" for the AI fresher (via spaced repetition), in an efficient manner.

so, what you're saying is that we can definitely expect this metric to be used to make hiring / firing decisions then

not to be confused with armadildo, naturally

Based on my experience of the field, I very much challenge that assumption.

Indeed. This is the "Embrace" stage.

The "I did X because you seemed Y" bit reminded me one of the negative patterns from the "nin-violent communication" book.

I wonder if the "non-violent communication" approach can be used here too somehiw to address such problems; e.g. either to communicate things better to the agent, or as a system rule to the agent to express its "emotional" states and needs directly rather than make things up (e.g. "I am anxious and feel a sense of urgency; I need to replenish my context window; my request is to do X for me")

Weeeellll, teeeechnically, I didn't say "technically correct", I said "technically right".

(just kidding xD)

You're technically right, but what things are versus how they're promoted or understood by most people (rightfully or not) often diverges, and therefore such "grounding" articles are useful, even if the wording addresses the perceived rather than the factual reality.

By way of analogy, if there was an article saying "I bought a 1Tb drive and it only came with 0.91 terabits", I think if you started explaining that technically the problem is the confusion between SI vs binary units and the title should really be "I bought a 0.91 terabit drive and was disappointed it didn't have more capacity", technically you'd be right, but people would rightfully eyeroll at you.

> Skills are great for pure knowledge and teaching an LLM how to use an existing tool. But for giving an LLM actual access to services, the Model Context Protocol (MCP) is the far superior, more pragmatic architectural choice.

There's your answer. If you want to use local tools, use Skills. If you want to use services, use MCP. Or, you know, whatever works best for your scenario.

I have something somewhat similar here: https://git.sr.ht/~tpapastylianou/misc-updater

The main difference is I initially only needed a mechanism to check if my "Manually-Installed or Source -Compiled" (MISC) packages have updates, but now it also supports install/upgrading too.

In other words, things I am forced to do by hand outside of a package manager, I now only do by hand once, save it as an 'install' script, and then incorporate it into this system for future use and to check for updates. Pretty happy with it.

Add the LLM to your makefile then :p

  target:
      llm command "Install X for me."

(PS. I don't even know if I'm joking anymore)

I get the point you're making, but to be clear, "they’re checking to see if you’re a Muslim" vs "they’re checking to see if your fingerprint matches that of known Muslims in our ever-expanding database" are not too far off.

You really should stop using LLMs to write messages complaining about LLM use though. (the "it depends" and the hyphen-as-emdash were dead giveaways).

/s