> Take the Unc Test and find out how cooked your aura really is.

Okay, as i get older i run into more of these scenarios where the new lingo is mostly beyond me. However this is not a complaint, if anything i'm more confused at how i grew up hearing "it'll happen to you!!" doom and gloom over frustration of youth lingo, yet i revel in it.

I find it fun in the way that new languages are fun, minus most of the work. Usually the new phrases are just a new word or two, far from the effort of learning a real new language.

And as a bonus you can then use the new lingo and make the youth groan out of second hand embarrassment. It really is a joy that i don't get why my older folks from my youth didn't enjoy. Then again i have zero concern about getting older (beyond health decline of course), so maybe that's the root of it.

Regardless, i bet i'm Unc. Lets see.

edit: Unc Score: 30, Soft Unc

- https://web.archive.org/web/20260602130637/https://www.techn... - https://web.archive.org/web/20260520190620/https://fortune.c...

I feel like writing could use a similar harness, where it attempts to minimally reword the authors sentences, perhaps just tweaking grammar, spelling, etc. In the coding example i think the human code would be near unchangeable, the LLM would pivot around it - but in the writing example i think the human writing would have to be more mutable. I imagine it would be a configurable setting.

I've not really seen a system which focuses on this human<->LLM look, but it feels interesting to me.

I think you're missing one (or more) of the facets individuals decide "better" is, for the subjective individual.

Early on i hopped between all the providers. Code quality for SOTA at the time was pretty decent if you didn't ask it to solve challenging problems. However the thing i found most difficult is consistency in how it listened. Eg Gemini (i forget what version, not current) was super prone to focusing solely on the functionality/goal, but not any of the directions on how to write the code. It would throw in comments everywhere, document in a manner i didn't want, use abstractions i told it not to, etc.

How well a model would follow instructions to drop their horrible "isms" was the #1 criteria for me. If i have to constantly remind the model not to do X behavior then it's a terrible model.

With that said, that is why i chose Claude for the last N months. However i've stuck with Claude because dealing with these "isms" and their little behavioral nuances is a chore in itself. I've found you have to learn the model just as much as anything, and so the idea of hopping these days when i'm just trying to get shit done is not likely.

These days for me personally, Claude has to give me a reason to switch rather than me investing even more money (i'm on the 20x plan) in other providers. I'm definitely not committed to Claude Code, but i am tired of the LLM churn, tooling churn, subscription churn, and the general fear of which providers we can trust.

edit: In short, it's the interactive UX just as much as it is the final output.

Am i reading this right? Seems to suggest that this can be used with Claude Code Subscription, which isn't true i think. Did this pre-date the CC Subscription change? Or is it playing fast and loose with the rules hah.

Maybe it's using `-p`, which technically works for another few days i think lol. (That's going away.. what, June 1st? Something like that?)

But that would be banned almost instantly i'm sure lol.

So yea, bcherny didn't reply to me but as far as i can tell - No, Zed nor VSCode will have Claude Code natively in it. The best we can do is embed a Terminal into the editor and run CC in that.

With that said, because bcherny advertised VSCode, i'm going to guess VSCode is going to get special treatment. Really annoying.

As usual though it's not super clear exactly what is allowed or not.

Eg is Zed capable of using a Claude Code Subscription?

I’m not aware of anything fundamentally unique about skills or commands, they’re just more tokens to shape the llm

Ironically i'm probably a better dev purely because after a few experiences on SO, I would rather waste days/weeks banging my head against problems and learning from them than to actually post on SO. It was a miserable experience generally. For context this was probably ~15 years ago now.

This isn't necessarily to say that SO made me a better developer. Rather i'm just saying that i value (correctly or not) those extremely hard fought lessons. Those lessons where it was considerable pain, effort, time, misery, etc. Are they efficient ways to learn? I doubt it. But in my many trips down that road i developed intuition that i'd probably not have otherwise.

So ironically i guess SO made me a better developer by avoiding using SO at all cost. Conversely, i imagine i'd lack this value that i speak of entirely if i was 20 years younger and starting fresh today. Not sure i'd be better off though.

edit: By "using SO" i should be saying posting on SO. I of course searched and used data found on SO as often as i could. So to that end i am grateful for SO existing.

The "cost" is dumb models is just so high for me. Eg every bad decision they make increases my frustration quite a bit. Despite putting a lot of effort into my workflow to help reduce the number of decisions they make, they always will. So my hedge is always against that.. trying to reduce how insane they can be heh.

I used to surf the three big players frequently and got really tired of the effort needed to steer some models. In the end i ended up sticking with Claude because it required less steering effort. While not strictly reasoning, a models ability to follow clear directions consistently is something i'd consider part of its SOTA capabilities.

Eventually i just tired of exploring. I just want stability.

Which ironically is why i'm thinking about moving from Claude. The very basic IDE/-p usage getting removed from my plan is a UX stability issue. I'm trying to progressively improve my workflows and efficiency, not have to establish a new foundation anytime something shifts. Quite frustrating.

I'm concerned since i really want SOTA reasoning, but DeepSeek still has me interested.

I think the same, and it's why i stopped caring about running llama/etc at home last year. That coupled with the models being dumb by comparison to SOTA really make me fine with waiting.

But in a year or two it's going to be difficult to resist at home, assuming the pace of improvement holds.