alanwreath

This is the exact comment I’ve been waiting for, what is the difference between classifiers and jev?

I read that like the meme:

<guy with messy hair>Aliens</guy with messy hair>

I too have been distro hopping, loading up Claude has made it extremely easy to be comfortable in exploring other distros

This is hilarious.

At first I thought spec driven development would be an obvious solution to the deficiencies you’d laid out, but thinking a little more I’m concerned my original words and prompts which are “captured” in the roadmap, tech-stack, mission and the in subsequent feature documents doesn’t always preserve the exact prompt I’ve given and I’m concerned that something I said would be lost and then forgotten.

Doing the whole “pay per token rate” when logging into a harness not made by them is not only being enforced by anthropic/claude though. It also is what Google does with agy (their TUI).

Is there any provider that doesn’t do this? That’s the one I want to support.

  > TLDR: they are all probably doing it because they are banking on you not using all your tokens.

I would be surprised though, it makes business sense to make the default vendor native TUI cheaper because it’s understood that most nascent users will just use the harness offered by the LLM provider and those that would stray off that would probably be more power users who would spend their token share more consistently till it drains.

There are so many stereotypes involved in this that it may be hard to believe but at least I know I have caught myself repeating the stereotype almost to a T (especially with regard to the oldest being worked so hard or, as I would put it, constantly on the hardest jobs).

That said it does help that it’s a stereotype/generalization/trope that I’m aware of because I get to take that as part of my feedback loop to make the attempt to iterate around the negative aspects you’ve pointed out.

I think I’m doing better - I’ll know if my kids still talk to me after they move out.

This is the take I pursue in my home, everyone is doing a see one, do one, teach one. There are still struggles around it but consistency makes the conversations shorter and more effective.

I don’t know about you, but sometimes ambition is just to put food on the table. That’s all it’s ever got me and the rest is the dream to escape a life of work work work.

I mean: siblings.

Not to discount that it’s great when you play with your kids, but it’s different when your kids play together, and in particular when you can’t play that they have someone to interact with.

That probably is exactly what is being referred to: the combination of low quality contractors who have access to AI means even more slop to wade through.

If AI is a 10xer the question is what is it 10xing.

If this were at all true, now read it like the big wig or law maker holding the on/off lever who’s eyes see “Universal Health Coversge Could reduce $1T in available/taxable income”.

Did you notice the gorilla walk by? They sure didn’t.

> 3.8-27B announced for Friday

Maybe I’m misreading this or some other post, I thought QWEN was stepping away from releasing these models for local consumption

I wish there were more games like this. It’s such a simple premise but so satisfyingly difficult after each level. And it even has a bit of randomish failure which makes for even more challenge.

Nice can’t wait for the linux port coming up.

I’m running my development from a Mac which I think precludes flatpack usage. Pity because I love the control you have over git

I’m not really here to defend opencode (or bash it, who has the time?), but in setting up SDD paired with the right tools to both make deterministic black boxes out of certain actions, paired with subagents. I have ran with opencode and qwen 3.2 on a 5090 and I’m getting results on a production codebase of golang where a review of changes from Claude had no changes but acceptance of the solution.

I may be missing some aspect of where the local llm’s are losing, but I’m content with draining my local tokens and treating the frontier models like a less junior SWE.

Nadella asks the question: why do foundational model providers get to tell you what knowledge you are entitled to access while at the same time engorging themselves on all your data scrupulously.

Could it also be that the phrase “using an LLM” is loaded in itself? Who is getting more velocity out of it:

- chat box interaction

- vendor harness user (the cursor / antigravity crowd)

- SDD Claude users

- bespoke harness creators who let it goooooooo

I mean we already know who’s using all the tokens and driving enough cost to make penny pinchers consider removing other “costs”

The tool isn't going away, it _is_ useful, but it's also a footgun and a slow suffocation. So learning to live with it and learning how to mitigate those issues is like any other tool adopted.

yes I want a post about that background, its pretty awesome how it gradually and seemingly randomly builds itself.

Yes! Recently connected two disparate systems (ubiquiti and mimrotik) using their exposed API’s and a Claude session so that systems I have on either environment could talk to each other. I am not a network engineer so it was liberating to get my gear working together. That said it’s a work in progress and just today I noticed something weird that one of my computers can’t access Minecraft servers while the rest of my network can

I stand by my comments. Bazzite has benefits being immutable but immutability can cause certain tasks to be more involved or constrained. Case in point it’s nice that Bazzite comes with a lot of sane defaults:

  - brew
  - podman

But it would be disingenuous to understate the additional hurdles either you or software you are accustomed to using being amenable to operating within the immutability restriction. That’s not to discount the great benefits and entire categories of problems that immutability protects you from. It’s just a priority and weighing your options question.

Here’s an example that bit me: I wanted to run k3s/k0s but both have issue with Bazzite. Those were hard stops for me.

Bazzite or CacheyOS (if you wish to do gaming and have more rope to hang yourself mainly because you can more easily affect the system if it isn’t trying to enforce immutability).

TBH with the onslaught of LLM CLI’s like Claude I am a lot more promiscuous in my Linux OS choices as of late. I used to stick to Ubuntu because that was the Linux I knew, but the “interface” has become the same to me because I just ask Claude to help me achieve a semantic goal without having to score the web for the appropriate keys.

Who knows, maybe I’ll eventually swing the other way and give NixOS a try finally.

This does not load for me.

I thought they prohibited the Apple mdm for family use. Was this a soft ban? Can we just use it without like verifying it’s just for the family?

Problem isn’t with “tastes better and at half the calories”, no, it is actually for providing filler when the initial sell was using genuine simple ingredients.

The software analog is like a certain Italian company that buys SaaS companies and waters down the initial product, firing then very ingredients that made the product good in the first place in an effort to:

- extract maximum profit

- ride the coattails of trust a brand has garnered.

I won’t speak to the odd coincidence of their name and its relation to ice cream.

Some people aren’t buying icecream to lose weight. That’s not their purpose. It’s to indulge and enjoy artisanal foods where the purpose was high quality not high margins.

Of course I don’t buy that icecream much anymore - I just buy Andies custard by the quart.

That’s Valve (somewhat) and Blizzard (but to the nth degree) in a nutshell.

That said, tangentially, I do wish game companies would let games live on.

I assume the same, but not because it’s sanctioned. Sanctioning is a slippery slope or a degree change as has been mentioned.

“Maintainability” is probably the word you are really looking for. Few devs care whether something adheres to whatever as long as we maintain:

- user experience/expectation (i.e., if feature X worked three years ago, it still works in a consistent way today after a bug fix) - development cadence (if implementation of feature X took N days, a comparable feature Y should take N days) - sanity (can we assume that a fix going in Thursday night or Friday morning doesn’t wreck the weekend)

SOLID, DRY, ACID-compliant, linted, formatted, clean, functional, compositional, etc. May be the means (misdirected or otherwise) but they are not the motivator(or at least should not be).

What matters is whether the day two feature requests, bug reports, CVEs, and traffic load that are coming can be met on time.

Not saying it can’t be done without a developer at the helm, Anyone Can Cook™, but I guess it depends on what harness is in use or has created for the org, and whether that consideration is baked into the guidelines for the codebase (which seems to be, at least to some extent, what this service tries to course correct).

And of course, what is done to the process when incident x happens, again and again. Are we only updating code without paying attention to process that enabled it in the first place?

Maybe that’s the story of vibe coded repos: the code devs were removed but we really still need devops personnel. Also maybe new tech will be more readily adopted.

Interesting times.